Skip to content

Actions: pytorch/FBGEMM

Actions

FBGEMM_GPU-CUDA CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
fbgemm_gpu_ci_cuda.yml
5,196 workflow runs
5,196 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

FBGEMM_GPU-CUDA CI FBGEMM_GPU-CUDA CI #5536: Scheduled
October 6, 2024 12:53 1h 6m 21s main
main
October 6, 2024 12:53 1h 6m 21s
Fix permute_multi_embedding kernel (#3227) FBGEMM_GPU-CUDA CI #5535: Commit 1815f89 pushed by facebook-github-bot
October 5, 2024 22:55 2h 9m 27s main
main
October 5, 2024 22:55 2h 9m 27s
Add support for int64_t indices and offsets in TBE inference [7C/N] (… FBGEMM_GPU-CUDA CI #5534: Commit 9408072 pushed by facebook-github-bot
October 5, 2024 21:40 1h 15m 56s main
main
October 5, 2024 21:40 1h 15m 56s
Fix permute_multi_embedding kernel FBGEMM_GPU-CUDA CI #5533: Pull request #3227 opened by xw285cornell
October 5, 2024 18:06 1h 1m 13s xw285cornell:export-D63936776
xw285cornell:export-D63936776
October 5, 2024 18:06 1h 1m 13s
Add configs from ROCm/triton tune_gemm (#3226) FBGEMM_GPU-CUDA CI #5532: Commit 42dca08 pushed by facebook-github-bot
October 5, 2024 13:37 1h 1m 36s main
main
October 5, 2024 13:37 1h 1m 36s
FBGEMM_GPU-CUDA CI FBGEMM_GPU-CUDA CI #5531: Scheduled
October 5, 2024 12:53 44m 14s main
main
October 5, 2024 12:53 44m 14s
Add support for int64_t indices and offsets in TBE inference [7C/N] FBGEMM_GPU-CUDA CI #5530: Pull request #3215 synchronize by q10
October 5, 2024 04:18 1h 0m 49s q10:export-D63778645
q10:export-D63778645
October 5, 2024 04:18 1h 0m 49s
Add support for int64_t indices and offsets in TBE inference [7C/N] FBGEMM_GPU-CUDA CI #5529: Pull request #3215 synchronize by q10
October 5, 2024 01:15 1h 4m 39s q10:export-D63778645
q10:export-D63778645
October 5, 2024 01:15 1h 4m 39s
Fix clang vla warning FBGEMM_GPU-CUDA CI #5527: Pull request #2736 synchronize by cyyever
October 4, 2024 23:13 Action required cyyever:vla
cyyever:vla
October 4, 2024 23:13 Action required
Fine-tune FP8 BMM performance (#3224) FBGEMM_GPU-CUDA CI #5526: Commit 7a4472a pushed by facebook-github-bot
October 4, 2024 23:11 1h 18m 27s main
main
October 4, 2024 23:11 1h 18m 27s
Allow N-D inputs to triton fp8 row quantize FBGEMM_GPU-CUDA CI #5525: Pull request #3225 opened by jwfromm
October 4, 2024 22:09 1h 8m 23s jwfromm:export-D63921964
jwfromm:export-D63921964
October 4, 2024 22:09 1h 8m 23s
Add support for int64_t indices and offsets in TBE inference [7C/N] FBGEMM_GPU-CUDA CI #5524: Pull request #3215 synchronize by q10
October 4, 2024 21:24 1h 0m 25s q10:export-D63778645
q10:export-D63778645
October 4, 2024 21:24 1h 0m 25s
Add support for int64_t indices and offsets in TBE inference [7C/N] FBGEMM_GPU-CUDA CI #5523: Pull request #3215 synchronize by q10
October 4, 2024 21:05 20m 19s q10:export-D63778645
q10:export-D63778645
October 4, 2024 21:05 20m 19s
Fix pack_segments backward when grad is non-contig (#3222) FBGEMM_GPU-CUDA CI #5522: Commit 88ef5f9 pushed by facebook-github-bot
October 4, 2024 20:36 1h 20m 17s main
main
October 4, 2024 20:36 1h 20m 17s
Redefine FBGEMM targets with gpu_cpp_library [27/N] FBGEMM_GPU-CUDA CI #5521: Pull request #3221 synchronize by q10
October 4, 2024 18:07 58m 23s q10:export-D63873905
q10:export-D63873905
October 4, 2024 18:07 58m 23s
Redefine FBGEMM targets with gpu_cpp_library [27/N] FBGEMM_GPU-CUDA CI #5520: Pull request #3221 synchronize by q10
October 4, 2024 18:02 4m 43s q10:export-D63873905
q10:export-D63873905
October 4, 2024 18:02 4m 43s
Rowwise F8F8BF16 GEMMs - Add to Quantize Bench FBGEMM_GPU-CUDA CI #5519: Pull request #3220 synchronize by manishucsd
October 4, 2024 17:22 Action required manishucsd:export-D63857729
manishucsd:export-D63857729
October 4, 2024 17:22 Action required
Rowwise F8F8BF16 GEMMs - Add to Quantize Bench FBGEMM_GPU-CUDA CI #5518: Pull request #3220 synchronize by manishucsd
October 4, 2024 17:14 Action required manishucsd:export-D63857729
manishucsd:export-D63857729
October 4, 2024 17:14 Action required
MoE BMM INT4 rowwise weight-only (#3219) FBGEMM_GPU-CUDA CI #5517: Commit d3eae1d pushed by facebook-github-bot
October 4, 2024 16:46 1h 0m 7s main
main
October 4, 2024 16:46 1h 0m 7s
Fine-tune FP8 BMM performance FBGEMM_GPU-CUDA CI #5516: Pull request #3224 synchronize by jiawenliu64
October 4, 2024 16:38 1h 3m 56s jiawenliu64:export-D63882833
jiawenliu64:export-D63882833
October 4, 2024 16:38 1h 3m 56s
FBGEMM_GPU-CUDA CI FBGEMM_GPU-CUDA CI #5515: Scheduled
October 4, 2024 12:55 1h 4m 1s main
main
October 4, 2024 12:55 1h 4m 1s
Fine-tune FP8 BMM performance FBGEMM_GPU-CUDA CI #5514: Pull request #3224 opened by jiawenliu64
October 4, 2024 07:47 1h 12m 16s jiawenliu64:export-D63882833
jiawenliu64:export-D63882833
October 4, 2024 07:47 1h 12m 16s
c10:optional -> std::optional in fbgemm FBGEMM_GPU-CUDA CI #5513: Pull request #3223 opened by r-barnes
October 4, 2024 05:57 1h 0m 54s r-barnes:export-D63876537
r-barnes:export-D63876537
October 4, 2024 05:57 1h 0m 54s
Redefine FBGEMM targets with gpu_cpp_library [27/N] FBGEMM_GPU-CUDA CI #5512: Pull request #3221 synchronize by q10
October 4, 2024 05:07 1h 1m 28s q10:export-D63873905
q10:export-D63873905
October 4, 2024 05:07 1h 1m 28s
Redefine FBGEMM targets with gpu_cpp_library [27/N] FBGEMM_GPU-CUDA CI #5511: Pull request #3221 synchronize by q10
October 4, 2024 04:11 56m 34s q10:export-D63873905
q10:export-D63873905
October 4, 2024 04:11 56m 34s