Skip to content

Actions: pytorch/FBGEMM

Actions

FBGEMM_GPU GenAI CI (Generic Runner)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
fbgemm_gpu_ci_genai_generic_infra.yml
9,253 workflow runs
9,253 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Disable SWA related decode kernel tests since they are not supported FBGEMM_GPU GenAI CI (Generic Runner) #10180: Pull request #4911 synchronize by Alkaid-Benetnash
2s Alkaid-Benetnash:export-D82991496
Alkaid-Benetnash:export-D82991496
2s
Triton early prune config fix FBGEMM_GPU GenAI CI (Generic Runner) #10179: Pull request #4917 opened by sunfish2010
3s sunfish2010:export-D83019498
sunfish2010:export-D83019498
3s
Add cutlass decode kernel to TritonBench FBGEMM_GPU GenAI CI (Generic Runner) #10178: Pull request #4853 synchronize by Aya-ZIbra
2s Aya-ZIbra:export-D80041532
Aya-ZIbra:export-D80041532
2s
Support bf16 in blackwell cutlass decode attention kernel FBGEMM_GPU GenAI CI (Generic Runner) #10177: Pull request #4916 opened by Aya-ZIbra
Action required Aya-ZIbra:export-D82991495
Aya-ZIbra:export-D82991495
Action required
Update to use Python 3.9 syntax (#4909) FBGEMM_GPU GenAI CI (Generic Runner) #10176: Commit a9a74e3 pushed by facebook-github-bot
1s main
main
1s
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU GenAI CI (Generic Runner) #10175: Pull request #4891 synchronize by jiawenliu64
1s export-D82700455
export-D82700455
1s
Optimize wgrad CUTLASS grouped gemm (#4891) FBGEMM_GPU GenAI CI (Generic Runner) #10174: Commit 5477513 pushed by jiawenliu64
1s export-D82700455
export-D82700455
1s
Support multiple total-k and total-m in quantize bench FBGEMM_GPU GenAI CI (Generic Runner) #10173: Pull request #4890 synchronize by jiawenliu64
1s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
1s
Support multiple total-k and total-m in quantize bench FBGEMM_GPU GenAI CI (Generic Runner) #10172: Pull request #4890 synchronize by jiawenliu64
1s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
1s
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU GenAI CI (Generic Runner) #10171: Pull request #4891 synchronize by jiawenliu64
2s export-D82700455
export-D82700455
2s
Optimize wgrad CUTLASS grouped gemm (#4891) FBGEMM_GPU GenAI CI (Generic Runner) #10170: Commit 15fa951 pushed by jiawenliu64
1s export-D82700455
export-D82700455
1s
Support multiple total-k and total-m in quantize bench FBGEMM_GPU GenAI CI (Generic Runner) #10169: Pull request #4890 synchronize by jiawenliu64
1s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
1s
Resolve wgrad grouped gemm relocation issue in fbgemm FBGEMM_GPU GenAI CI (Generic Runner) #10168: Pull request #4915 opened by jiawenliu64
1s export-D83020887
export-D83020887
1s
Resolve wgrad grouped gemm relocation issue in fbgemm FBGEMM_GPU GenAI CI (Generic Runner) #10167: Commit 8aaf3a7 pushed by jiawenliu64
1s export-D83020887
export-D83020887
1s
Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 (resubmit) FBGEMM_GPU GenAI CI (Generic Runner) #10166: Pull request #4913 synchronize by jiawenliu64
1s jiawenliu64:export-D83001505
jiawenliu64:export-D83001505
1s
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU GenAI CI (Generic Runner) #10165: Pull request #4891 synchronize by jiawenliu64
1s export-D82700455
export-D82700455
1s
Optimize wgrad CUTLASS grouped gemm (#4891) FBGEMM_GPU GenAI CI (Generic Runner) #10164: Commit 78c96a2 pushed by jiawenliu64
1s export-D82700455
export-D82700455
1s
Cut over coalesce ops (#4910) FBGEMM_GPU GenAI CI (Generic Runner) #10163: Commit f7bb933 pushed by facebook-github-bot
1s main
main
1s
Remove e5m2 from f8f8bf16_rowwise_batched (#4908) FBGEMM_GPU GenAI CI (Generic Runner) #10162: Commit 033bad0 pushed by facebook-github-bot
1s main
main
1s
[fbgemm_gpu] Fix IndicesEstimator constructor FBGEMM_GPU GenAI CI (Generic Runner) #10161: Pull request #4906 synchronize by cyyever
3s cyyever:IndicesEstimator_constructor
cyyever:IndicesEstimator_constructor
3s
Migrate GenAI gqa attn splitk kernels to FBGEMM_LAUNCH_KERNEL, pt 2 FBGEMM_GPU GenAI CI (Generic Runner) #10160: Pull request #4914 opened by q10
Skipped q10:export-D81829067
q10:export-D81829067
Skipped
fix the scaled input issue (#4884) FBGEMM_GPU GenAI CI (Generic Runner) #10159: Commit 78f7058 pushed by facebook-github-bot
1s main
main
1s
Migrate GenAI gqa attn splitk kernels to FBGEMM_LAUNCH_KERNEL, pt 1… FBGEMM_GPU GenAI CI (Generic Runner) #10158: Commit 0988166 pushed by facebook-github-bot
1s main
main
1s
Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 (resubmit) FBGEMM_GPU GenAI CI (Generic Runner) #10157: Pull request #4913 opened by jiawenliu64
2s jiawenliu64:export-D83001505
jiawenliu64:export-D83001505
2s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU GenAI CI (Generic Runner) #10156: Pull request #4912 synchronize by seanx92
1s seanx92:export-D82507938
seanx92:export-D82507938
1s