Skip to content

Actions: pytorch/FBGEMM

Actions

FBGEMM_GPU-ROCm Benchmark

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
fbgemm_gpu_benchmark_rocm.yml
5,004 workflow runs
5,004 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add Inference Feature to Skip Pinned Memory Creation (#1948) FBGEMM_GPU-ROCm Benchmark #5710: Pull request #4924 synchronize by Jason-KChen
12m 37s Jason-KChen:export-D83100663
Jason-KChen:export-D83100663
12m 37s
Split grouped gemm metadata kernel into grouped_common.cuh FBGEMM_GPU-ROCm Benchmark #5709: Pull request #4932 synchronize by cthi
1h 7m 13s cthi:export-D83151150
cthi:export-D83151150
1h 7m 13s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU-ROCm Benchmark #5708: Pull request #4912 synchronize by seanx92
1h 18m 55s seanx92:export-D82507938
seanx92:export-D82507938
1h 18m 55s
FP4 grouped refactor FBGEMM_GPU-ROCm Benchmark #5707: Pull request #4934 opened by cthi
1h 8m 34s cthi:export-D83166227
cthi:export-D83166227
1h 8m 34s
Add output as an option in CUTLASS grouped GEMM FBGEMM_GPU-ROCm Benchmark #5706: Pull request #4931 synchronize by jiawenliu64
57m 55s jiawenliu64:export-D83126291
jiawenliu64:export-D83126291
57m 55s
Fix typo in FP4 quantize FBGEMM_GPU-ROCm Benchmark #5705: Pull request #4933 opened by cthi
58m 40s cthi:export-D83083612
cthi:export-D83083612
58m 40s
Split grouped gemm metadata kernel into grouped_common.cuh FBGEMM_GPU-ROCm Benchmark #5704: Pull request #4932 opened by cthi
1h 8m 9s cthi:export-D83151150
cthi:export-D83151150
1h 8m 9s
more hipify v2 fixes (#4854) FBGEMM_GPU-ROCm Benchmark #5703: Pull request #4921 synchronize by q10
56m 48s q10:export-D82186865
q10:export-D82186865
56m 48s
Migrate GenAI gqa attn splitk kernel arguments to use PTA_B FBGEMM_GPU-ROCm Benchmark #5702: Pull request #4922 synchronize by q10
1h 32m 32s q10:export-D81829444
q10:export-D81829444
1h 32m 32s
Add output as an option in CUTLASS grouped GEMM FBGEMM_GPU-ROCm Benchmark #5701: Pull request #4931 synchronize by jiawenliu64
1h 9m 38s jiawenliu64:export-D83126291
jiawenliu64:export-D83126291
1h 9m 38s
Add output as an option in CUTLASS grouped GEMM FBGEMM_GPU-ROCm Benchmark #5700: Pull request #4931 opened by jiawenliu64
11m 47s jiawenliu64:export-D83126291
jiawenliu64:export-D83126291
11m 47s
Disable test_decode FBGEMM_GPU-ROCm Benchmark #5698: Pull request #4929 opened by sryap
56m 25s sryap:export-D83111500
sryap:export-D83111500
56m 25s
Back out "Update to use Python 3.9 syntax" FBGEMM_GPU-ROCm Benchmark #5697: Pull request #4928 synchronize by q10
1h 1m 58s q10:export-D83123698
q10:export-D83123698
1h 1m 58s
Back out "Update to use Python 3.9 syntax" FBGEMM_GPU-ROCm Benchmark #5696: Pull request #4928 opened by q10
9m 1s q10:export-D83123698
q10:export-D83123698
9m 1s
Add Static Dispatch Kernels FBGEMM_GPU-ROCm Benchmark #5695: Pull request #4927 opened by kqfu
1h 0m 8s kqfu:export-D83028503
kqfu:export-D83028503
1h 0m 8s
Add unit tests for TBE API v1 compatibility FBGEMM_GPU-ROCm Benchmark #5694: Pull request #4926 synchronize by spcyppt
59m 9s spcyppt:export-D83020965
spcyppt:export-D83020965
59m 9s
Add unit tests for TBE API v1 compatibility FBGEMM_GPU-ROCm Benchmark #5693: Pull request #4926 opened by spcyppt
1h 8m 23s spcyppt:export-D83020965
spcyppt:export-D83020965
1h 8m 23s
forward performance tuning for MI350 FBGEMM_GPU-ROCm Benchmark #5692: Pull request #4925 opened by liligwu
1h 23m 6s ROCm:mi350_dev
ROCm:mi350_dev
1h 23m 6s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU-ROCm Benchmark #5690: Pull request #4912 synchronize by seanx92
52m 4s seanx92:export-D82507938
seanx92:export-D82507938
52m 4s
Add Inference Feature to Skip Pinned Memory Creation (#1948) FBGEMM_GPU-ROCm Benchmark #5689: Pull request #4924 opened by Jason-KChen
16m 37s Jason-KChen:export-D83100663
Jason-KChen:export-D83100663
16m 37s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU-ROCm Benchmark #5688: Pull request #4912 synchronize by seanx92
54m 23s seanx92:export-D82507938
seanx92:export-D82507938
54m 23s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU-ROCm Benchmark #5687: Pull request #4912 synchronize by seanx92
25m 26s seanx92:export-D82507938
seanx92:export-D82507938
25m 26s
Fix clang-tidy and nvcc warnings (#4918) FBGEMM_GPU-ROCm Benchmark #5686: Pull request #4923 opened by q10
1h 3m 28s q10:export-D83070110
q10:export-D83070110
1h 3m 28s
MI350X FP8 triton patch FBGEMM_GPU-ROCm Benchmark #5685: Pull request #4889 synchronize by JChunX
Action required JChunX:export-D81180838
JChunX:export-D81180838
Action required
avx512 based int8 -> bf16 dequantization FBGEMM_GPU-ROCm Benchmark #5684: Pull request #4912 synchronize by seanx92
34m 4s seanx92:export-D82507938
seanx92:export-D82507938
34m 4s