[ExecuTorch][WebGPU] Op-tests for conv_with_clamp#21218
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21218
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 63b4386 with merge base 4a26c64 ( 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: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
JCNTH
added a commit
that referenced
this pull request
Jul 24, 2026
Pull Request resolved: #21218 Problem: The new `et_vk.conv_with_clamp` op (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs. Solution: `ConvWithClampModule` is a plain `nn.Conv2d` + `F.relu6`, which the Vulkan fusion rewrites to `et_vk.conv_with_clamp` (fp32 conv + clamp[0,6]); the conv weight/bias are baked params and only `x` is a runtime input. Goldened vs the module's fp32 eager. The `asym` case is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden. Implementation: `cases.py` registers `conv_with_clamp` with `k3p1`/`stride2`/`dil2`/`no_bias`/`asym` (all groups==1); `test_conv_with_clamp.py` holds the module + a delegation smoke test asserting `et_vk.conv_with_clamp` is absorbed into the VulkanBackend delegate. ghstack-source-id: 406366873 @exported-using-ghexport Differential Revision: [D112257609](https://our.internmc.facebook.com/intern/diff/D112257609/)
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 new
et_vk.conv_with_clampop (a first-of-its-kind general fp32 conv2d) needs golden coverage that exercises the H/W axis separation, not just square/symmetric configs.Solution:
ConvWithClampModuleis a plainnn.Conv2d+F.relu6, which the Vulkan fusion rewrites toet_vk.conv_with_clamp(fp32 conv + clamp[0,6]); the conv weight/bias are baked params and onlyxis a runtime input. Goldened vs the module's fp32 eager. Theasymcase is fully axis-asymmetric (input H=7≠W=9, kernel Kh=2≠Kw=3, stride 1≠2, padding 1≠0, dilation 2≠1 → output H_out=7≠W_out=4), so an H↔W index swap anywhere (unravel divisors, stride/pad/dilation axis, or Kh/Kw) diverges from the golden.Implementation:
cases.pyregistersconv_with_clampwithk3p1/stride2/dil2/no_bias/asym(all groups==1);test_conv_with_clamp.pyholds the module + a delegation smoke test assertinget_vk.conv_with_clampis absorbed into the VulkanBackend delegate.@exported-using-ghexport
Differential Revision: D112257609
Differential Revision: D112257609