Skip to content

Actions: ModelTC/LightX2V

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[ROCm] Run Sol-Attn on gfx1201 (RDNA4) through aiter lint #6423: Pull request #1599 opened by Shan2L
Action required Shan2L:feat/rocm-aiter-sol-attn
Shan2L:feat/rocm-aiter-sol-attn
Action required
[ROCm] Add aiter_sage_attn attention backend for gfx1201 (RDNA4) lint #6422: Pull request #1598 opened by Shan2L
Action required Shan2L:feat/rocm-aiter-sage-attn
Shan2L:feat/rocm-aiter-sage-attn
Action required
perf(dreamzero): accelerate NVIDIA Thor inference with FA4 and native kernels lint #6421: Pull request #1597 synchronize by Lunemere
21s Lunemere:feat/dreamzero-thor-native
Lunemere:feat/dreamzero-thor-native
21s
perf(dreamzero): accelerate NVIDIA Thor inference with FA4 and native kernels lint #6420: Pull request #1597 opened by Lunemere
24s Lunemere:feat/dreamzero-thor-native
Lunemere:feat/dreamzero-thor-native
24s
[ROCm] Opt-in deterministic FP32 GEMM/conv via rocBLAS lint #6419: Pull request #1596 opened by Shan2L
Action required Shan2L:fix/rocm-deterministic-fp32-blas
Shan2L:fix/rocm-deterministic-fp32-blas
Action required
Set PYTORCH_CUDA_ALLOC_CONF before platform init lint #6418: Pull request #1595 opened by Shan2L
Action required Shan2L:fix/rocm-alloc-conf-before-platform-init
Shan2L:fix/rocm-alloc-conf-before-platform-init
Action required
refactor: simplify inference configs and example scripts(v3) (#1592) lint #6417: Commit 4fe984c pushed by llmc-reviewer
25s main
main
25s
refactor: simplify inference configs and example scripts(v3) lint #6416: Pull request #1592 opened by zhangbilang
30s zhangbilang:pr
zhangbilang:pr
30s
Fix/training precision baseline (#1591) lint #6415: Commit 1f83487 pushed by helloyongyang
26s main
main
26s
Fix/training precision baseline lint #6414: Pull request #1591 opened by GoatWu
28s fix/training-precision-baseline
fix/training-precision-baseline
28s
Fix/training precision baseline (#1589) lint #6413: Commit 6101bff pushed by helloyongyang
25s main
main
25s
Fix/training precision baseline lint #6412: Pull request #1589 opened by GoatWu
28s fix/training-precision-baseline
fix/training-precision-baseline
28s
support qwen-image-2.1 vae tile infer (#1588) lint #6411: Commit 42f6e6f pushed by helloyongyang
31s main
main
31s
support qwen-image-2.1 vae tile infer lint #6410: Pull request #1588 opened by helloyongyang
34s hhk
hhk
34s
Support qwen-image-2.1 i2i for macbook mps (#1587) lint #6409: Commit 56ddb1d pushed by helloyongyang
22s main
main
22s
Support qwen-image-2.1 i2i for macbook mps lint #6408: Pull request #1587 opened by helloyongyang
29s hhk
hhk
29s
Support resolution for qwen-image-2.1 in server (#1586) lint #6407: Commit 8a39a6b pushed by helloyongyang
27s main
main
27s
Support resolution for qwen-image-2.1 in server lint #6406: Pull request #1586 opened by helloyongyang
31s qww
qww
31s
fix: audio refrence count (#1585) lint #6405: Commit b6d3828 pushed by helloyongyang
34s main
main
34s
fix: audio refrence count lint #6404: Pull request #1585 opened by Musisoul
29s fix_audio_count
fix_audio_count
29s
Refactor contiguous block offload and organize model launchers (#1570) lint #6403: Commit 913a974 pushed by helloyongyang
22s main
main
22s
update realtime readme (#1584) lint #6402: Commit 824a5b6 pushed by gushiqiao
22s main
main
22s
update realtime readme lint #6401: Pull request #1584 opened by chengtao-lv
29s wam
wam
29s
[AMD ROCm] 45:5 INT4/INT8 mixed precision sage attention kernels for MiniMax-H3 on gfx1201 lint #6400: Pull request #1583 opened by jundali77
Action required jundali77:mixed_precision_minimaxH3_gfx1201
jundali77:mixed_precision_minimaxH3_gfx1201
Action required
Ar ws lint #6399: Pull request #1512 synchronize by huochaitiantang
33s ar-ws
ar-ws
33s