Skip to content

Actions: pytorch/FBGEMM

Actions

FBGEMM GPU/GenAI/HSTU CUDA CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
fbgemm_gpu_ci_cuda.yml
10,068 workflow runs
10,068 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

more hipify v2 fixes (#4854) FBGEMM GPU/GenAI/HSTU CUDA CI #15422: Pull request #4921 synchronize by q10
59m 14s q10:export-D82186865
q10:export-D82186865
59m 14s
Migrate GenAI gqa attn splitk kernels to FBGEMM_LAUNCH_KERNEL, pt 2… FBGEMM GPU/GenAI/HSTU CUDA CI #15421: Commit 1eacb9e pushed by facebook-github-bot
2h 24m 49s main
main
2h 24m 49s
more hipify v2 fixes (#4854) FBGEMM GPU/GenAI/HSTU CUDA CI #15420: Pull request #4921 synchronize by q10
14m 45s q10:export-D82186865
q10:export-D82186865
14m 45s
more hipify v2 fixes (#4854) FBGEMM GPU/GenAI/HSTU CUDA CI #15419: Pull request #4921 synchronize by q10
10m 22s q10:export-D82186865
q10:export-D82186865
10m 22s
Fix IndicesEstimator constructor (#4906) FBGEMM GPU/GenAI/HSTU CUDA CI #15418: Commit 42600ba pushed by facebook-github-bot
24m 17s main
main
24m 17s
more hipify v2 fixes (#4854) FBGEMM GPU/GenAI/HSTU CUDA CI #15417: Pull request #4921 opened by q10
11m 51s q10:export-D82186865
q10:export-D82186865
11m 51s
Demonstration of per-op targets FBGEMM GPU/GenAI/HSTU CUDA CI #15416: Pull request #4919 synchronize by cthi
1h 1m 33s cthi:export-D83056686
cthi:export-D83056686
1h 1m 33s
add one mode in Rowwise_adagrad_with_counter FBGEMM GPU/GenAI/HSTU CUDA CI #15415: Pull request #4920 opened by dudongsu
Action required dudongsu:export-D82576034
dudongsu:export-D82576034
Action required
Optimize wgrad CUTLASS grouped gemm (#4891) FBGEMM GPU/GenAI/HSTU CUDA CI #15414: Commit ddada9e pushed by facebook-github-bot
42m 23s main
main
42m 23s
Demonstration of per-op targets FBGEMM GPU/GenAI/HSTU CUDA CI #15413: Pull request #4919 synchronize by cthi
8m 43s cthi:export-D83056686
cthi:export-D83056686
8m 43s
Optimize wgrad CUTLASS grouped gemm FBGEMM GPU/GenAI/HSTU CUDA CI #15412: Pull request #4891 synchronize by jiawenliu64
56m 9s export-D82700455
export-D82700455
56m 9s
Demonstration of per-op targets FBGEMM GPU/GenAI/HSTU CUDA CI #15411: Pull request #4919 opened by cthi
16m 50s cthi:export-D83056686
cthi:export-D83056686
16m 50s
Optimize wgrad CUTLASS grouped gemm FBGEMM GPU/GenAI/HSTU CUDA CI #15410: Pull request #4891 synchronize by jiawenliu64
15m 13s export-D82700455
export-D82700455
15m 13s
Optimize wgrad CUTLASS grouped gemm FBGEMM GPU/GenAI/HSTU CUDA CI #15409: Pull request #4891 synchronize by jiawenliu64
12m 31s export-D82700455
export-D82700455
12m 31s
Support multiple total-k and total-m in quantize bench FBGEMM GPU/GenAI/HSTU CUDA CI #15408: Pull request #4890 synchronize by jiawenliu64
1h 32m 31s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
1h 32m 31s
Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 (resubmit) FBGEMM GPU/GenAI/HSTU CUDA CI #15407: Pull request #4913 synchronize by jiawenliu64
1h 30m 40s jiawenliu64:export-D83001505
jiawenliu64:export-D83001505
1h 30m 40s
Optimize wgrad CUTLASS grouped gemm FBGEMM GPU/GenAI/HSTU CUDA CI #15406: Pull request #4891 synchronize by jiawenliu64
7m 18s export-D82700455
export-D82700455
7m 18s
Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 (resubmit) FBGEMM GPU/GenAI/HSTU CUDA CI #15405: Pull request #4913 synchronize by jiawenliu64
7m 13s jiawenliu64:export-D83001505
jiawenliu64:export-D83001505
7m 13s
Support multiple total-k and total-m in quantize bench FBGEMM GPU/GenAI/HSTU CUDA CI #15404: Pull request #4890 synchronize by jiawenliu64
10m 58s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
10m 58s
FBGEMM GPU/GenAI/HSTU CUDA CI FBGEMM GPU/GenAI/HSTU CUDA CI #15403: Scheduled
2h 54m 43s main
main
2h 54m 43s
Fix clang-tidy and nvcc warnings FBGEMM GPU/GenAI/HSTU CUDA CI #15402: Pull request #4918 opened by cyyever
2h 44m 49s cyyever:tidy_code3
cyyever:tidy_code3
2h 44m 49s
avx512 based int8 -> bf16 dequantization FBGEMM GPU/GenAI/HSTU CUDA CI #15401: Pull request #4912 synchronize by seanx92
2h 17m 26s seanx92:export-D82507938
seanx92:export-D82507938
2h 17m 26s
avx512 based int8 -> bf16 dequantization FBGEMM GPU/GenAI/HSTU CUDA CI #15400: Pull request #4912 synchronize by seanx92
38m 22s seanx92:export-D82507938
seanx92:export-D82507938
38m 22s
Disable SWA related decode kernel tests since they are not supported FBGEMM GPU/GenAI/HSTU CUDA CI #15399: Pull request #4911 synchronize by Alkaid-Benetnash
2h 27m 56s Alkaid-Benetnash:export-D82991496
Alkaid-Benetnash:export-D82991496
2h 27m 56s
Triton early prune config fix FBGEMM GPU/GenAI/HSTU CUDA CI #15398: Pull request #4917 opened by sunfish2010
2h 32m 54s sunfish2010:export-D83019498
sunfish2010:export-D83019498
2h 32m 54s