Skip to content

Actions: pytorch/FBGEMM

Actions

FBGEMM_GPU_TORCHREC-CPU CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
fbgemm_gpu_torchrec_ci_cpu.yml
748 workflow runs
748 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

MI350X FP8 triton patch FBGEMM_GPU_TORCHREC-CPU CI #717: Pull request #4889 synchronize by JChunX
51s JChunX:export-D81180838
JChunX:export-D81180838
51s
Add Static Dispatch Kernels FBGEMM_GPU_TORCHREC-CPU CI #716: Pull request #4927 synchronize by kqfu
2m 3s kqfu:export-D83028503
kqfu:export-D83028503
2m 3s
Add Static Dispatch Kernels FBGEMM_GPU_TORCHREC-CPU CI #715: Pull request #4927 synchronize by kqfu
7m 8s kqfu:export-D83028503
kqfu:export-D83028503
7m 8s
Add head_dim = 64 in B200 Attention. FBGEMM_GPU_TORCHREC-CPU CI #714: Pull request #4935 opened by gchalump
18m 8s gchalump:export-D82996471
gchalump:export-D82996471
18m 8s
Support bf16 in blackwell cutlass decode attention kernel FBGEMM_GPU_TORCHREC-CPU CI #713: Pull request #4916 synchronize by Aya-ZIbra
27m 20s Aya-ZIbra:export-D82991495
Aya-ZIbra:export-D82991495
27m 20s
Add Inference Feature to Skip Pinned Memory Creation (#1948) FBGEMM_GPU_TORCHREC-CPU CI #712: Pull request #4924 synchronize by Jason-KChen
36m 11s Jason-KChen:export-D83100663
Jason-KChen:export-D83100663
36m 11s
Add output as an option in CUTLASS grouped GEMM (#4931) FBGEMM_GPU_TORCHREC-CPU CI #711: Commit c1f22a9 pushed by facebook-github-bot
29m 2s main
main
29m 2s
Add Inference Feature to Skip Pinned Memory Creation (#1948) FBGEMM_GPU_TORCHREC-CPU CI #710: Pull request #4924 synchronize by Jason-KChen
11m 36s Jason-KChen:export-D83100663
Jason-KChen:export-D83100663
11m 36s
Split grouped gemm metadata kernel into grouped_common.cuh FBGEMM_GPU_TORCHREC-CPU CI #709: Pull request #4932 synchronize by cthi
41m 31s cthi:export-D83151150
cthi:export-D83151150
41m 31s
Fix typo in FP4 quantize (#4933) FBGEMM_GPU_TORCHREC-CPU CI #708: Commit bb87e43 pushed by facebook-github-bot
31m 29s main
main
31m 29s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU_TORCHREC-CPU CI #707: Pull request #4912 synchronize by seanx92
39m 4s seanx92:export-D82507938
seanx92:export-D82507938
39m 4s
Add unit tests for TBE API v1 compatibility (#4926) FBGEMM_GPU_TORCHREC-CPU CI #706: Commit 947e4e5 pushed by facebook-github-bot
17m 2s main
main
17m 2s
FP4 grouped refactor FBGEMM_GPU_TORCHREC-CPU CI #705: Pull request #4934 opened by cthi
33m 49s cthi:export-D83166227
cthi:export-D83166227
33m 49s
Add output as an option in CUTLASS grouped GEMM FBGEMM_GPU_TORCHREC-CPU CI #704: Pull request #4931 synchronize by jiawenliu64
31m 7s jiawenliu64:export-D83126291
jiawenliu64:export-D83126291
31m 7s
Fix typo in FP4 quantize FBGEMM_GPU_TORCHREC-CPU CI #703: Pull request #4933 opened by cthi
38m 25s cthi:export-D83083612
cthi:export-D83083612
38m 25s
Split grouped gemm metadata kernel into grouped_common.cuh FBGEMM_GPU_TORCHREC-CPU CI #702: Pull request #4932 opened by cthi
30m 31s cthi:export-D83151150
cthi:export-D83151150
30m 31s
FBGEMM_GPU_TORCHREC-CPU CI FBGEMM_GPU_TORCHREC-CPU CI #701: Scheduled
32m 14s main
main
32m 14s
more hipify v2 fixes (#4854) FBGEMM_GPU_TORCHREC-CPU CI #700: Pull request #4921 synchronize by q10
28m 24s q10:export-D82186865
q10:export-D82186865
28m 24s
Migrate GenAI gqa attn splitk kernel arguments to use PTA_B FBGEMM_GPU_TORCHREC-CPU CI #699: Pull request #4922 synchronize by q10
34m 19s q10:export-D81829444
q10:export-D81829444
34m 19s
Add output as an option in CUTLASS grouped GEMM FBGEMM_GPU_TORCHREC-CPU CI #698: Pull request #4931 synchronize by jiawenliu64
27m 12s jiawenliu64:export-D83126291
jiawenliu64:export-D83126291
27m 12s
Add output as an option in CUTLASS grouped GEMM FBGEMM_GPU_TORCHREC-CPU CI #697: Pull request #4931 opened by jiawenliu64
11m 1s jiawenliu64:export-D83126291
jiawenliu64:export-D83126291
11m 1s
Disable test_decode FBGEMM_GPU_TORCHREC-CPU CI #695: Pull request #4929 opened by sryap
31m 46s sryap:export-D83111500
sryap:export-D83111500
31m 46s
Back out "Update to use Python 3.9 syntax" FBGEMM_GPU_TORCHREC-CPU CI #694: Pull request #4928 synchronize by q10
1h 26m 25s q10:export-D83123698
q10:export-D83123698
1h 26m 25s
Back out "Update to use Python 3.9 syntax" FBGEMM_GPU_TORCHREC-CPU CI #693: Pull request #4928 opened by q10
8m 16s q10:export-D83123698
q10:export-D83123698
8m 16s
Remove unsupported parameters from decode kernel tests (#4911) FBGEMM_GPU_TORCHREC-CPU CI #692: Commit 826064d pushed by facebook-github-bot
27m 0s main
main
27m 0s