[ExecuTorch][WebGPU] Add conv_with_clamp op (et_vk.conv_with_clamp)#21217
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21217
Note: Links to docs will display an error until the docs builds have been completed. ❌ 47 New Failures, 2 Unrelated FailuresAs of commit 958a98b with merge base 4a26c64 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Jul 22, 2026
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21217 Problem: The WebGPU delegate has no `et_vk.conv_with_clamp` — a fused fp32 2D convolution + output clamp (e.g. a `Conv2d` followed by `relu6`). It delegates through `VulkanPartitioner` (`op_registry.py` tags `et_vk.conv_with_clamp.default`; `nn.Conv2d`+`F.relu6` fuses to it) but had no WebGPU handler. Solution: Port `et_vk.conv_with_clamp` (fp32, groups==1), mirroring the Vulkan `conv` handler (`impl/Convolution.cpp:837`) + the eager `clamp(convolution(...), output_min, output_max)` (`custom_ops_lib.py`). Direct windowed conv reusing the staged `q8ta_conv2d` windowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cell `out[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max)`, OOB taps skipped. Implementation: `conv_with_clamp/ConvWithClamp.cpp` registers `et_vk.conv_with_clamp.default` -> `conv_with_clamp_impl`. Args `[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]`; stride/padding/dilation as int-pairs, `output_min`/`output_max` as `Scalar?` (Double/Int -> value, absent -> -/+inf so `clamp` is a passthrough). `conv_with_clamp.wgsl`: one thread per output element, RAW `[OC,IC,Kh,Kw]` weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col `[OC,Kh*Kw*IC]`), 2D-folded dispatch. `ConvWithClampParams` (80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32, `weight.dims[1]==IC`, numel<=u32, groups==1 + not-transposed, all fail-loud. Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (`conv2d_prepack_weights.glsl`) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped to `groups==1` + not-transposed (fail-loud otherwise). Note: overlaps the general `convolution` op — this handles the clamped variant only. ghstack-source-id: 406366872 @exported-using-ghexport Differential Revision: [D112257644](https://our.internmc.facebook.com/intern/diff/D112257644/)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
Problem: The WebGPU delegate has no
et_vk.conv_with_clamp— a fused fp32 2D convolution + output clamp (e.g. aConv2dfollowed byrelu6). It delegates throughVulkanPartitioner(op_registry.pytagset_vk.conv_with_clamp.default;nn.Conv2d+F.relu6fuses to it) but had no WebGPU handler.Solution: Port
et_vk.conv_with_clamp(fp32, groups==1), mirroring the Vulkanconvhandler (impl/Convolution.cpp:837) + the eagerclamp(convolution(...), output_min, output_max)(custom_ops_lib.py). Direct windowed conv reusing the stagedq8ta_conv2dwindowing structure but fp32 (no int8 unpack/dequant/requant) + a clamp epilogue: per NCHW output cellout[n,oc,oh,ow] = clamp(bias[oc] + Σ_{ic,kh,kw} weight[oc,ic,kh,kw] * input[n,ic, oh*sh-ph+kh*dh, ow*sw-pw+kw*dw], output_min, output_max), OOB taps skipped.Implementation:
conv_with_clamp/ConvWithClamp.cppregisterset_vk.conv_with_clamp.default->conv_with_clamp_impl. Args[in, weight, bias?, stride, padding, dilation, transposed, output_padding, groups, output_min?, output_max?, out]; stride/padding/dilation as int-pairs,output_min/output_maxasScalar?(Double/Int -> value, absent -> -/+inf soclampis a passthrough).conv_with_clamp.wgsl: one thread per output element, RAW[OC,IC,Kh,Kw]weight (the fp32 buffer path gets the raw constant, like conv1d_dw/pw — not the q8ta im2col[OC,Kh*Kw*IC]), 2D-folded dispatch.ConvWithClampParams(80 bytes) matches the WGSL Params. Guards: in/weight/out 4D + fp32,weight.dims[1]==IC, numel<=u32, groups==1 + not-transposed, all fail-loud.Constraints / divergences from the Vulkan reference: buffer re-derivation of Vulkan's texture conv (
conv2d_prepack_weights.glsl) — the naive one-thread-per-output form is forced by the buffer-only backend. Scoped togroups==1+ not-transposed (fail-loud otherwise). Note: overlaps the generalconvolutionop — this handles the clamped variant only.@exported-using-ghexport
Differential Revision: D112257644
Differential Revision: D112257644