Skip to content

Actions: pytorch/FBGEMM

Actions

FBGEMM_GPU-CPU Benchmark

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
fbgemm_gpu_benchmark_cpu.yml
4,934 workflow runs
4,934 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Remove e5m2 from f8f8bf16_rowwise FBGEMM_GPU-CPU Benchmark #5613: Pull request #4907 synchronize by cthi
19m 19s cthi:export-D82965586
cthi:export-D82965586
19m 19s
Remove e5m2 from f8f8bf16_rowwise FBGEMM_GPU-CPU Benchmark #5612: Pull request #4907 opened by cthi
21m 31s cthi:export-D82965586
cthi:export-D82965586
21m 31s
[fbgemm_gpu] Fix IndicesEstimator constructor FBGEMM_GPU-CPU Benchmark #5611: Pull request #4906 opened by cyyever
13m 26s cyyever:IndicesEstimator_constructor
cyyever:IndicesEstimator_constructor
13m 26s
Update to use Python 3.9 syntax FBGEMM_GPU-CPU Benchmark #5610: Pull request #4905 synchronize by cyyever
17m 58s cyyever:ruff_fix
cyyever:ruff_fix
17m 58s
Update to use Python 3.9 syntax FBGEMM_GPU-CPU Benchmark #5609: Pull request #4905 opened by cyyever
Action required cyyever:ruff_fix
cyyever:ruff_fix
Action required
Correct the inaccurate docstring for int4_row_quantize() FBGEMM_GPU-CPU Benchmark #5608: Pull request #4904 opened by geng-meta
20m 30s geng-meta:export-D82919480
geng-meta:export-D82919480
20m 30s
Cleanup MSVC arguments in defs.bzl FBGEMM_GPU-CPU Benchmark #5607: Pull request #4903 opened by cyyever
19m 54s cyyever:defs_bzl_cleanup
cyyever:defs_bzl_cleanup
19m 54s
Fix ROCm build I broke FBGEMM_GPU-CPU Benchmark #5606: Pull request #4902 synchronize by cthi
19m 7s cthi:export-D82895451
cthi:export-D82895451
19m 7s
Fix ROCm build I broke FBGEMM_GPU-CPU Benchmark #5605: Pull request #4902 opened by cthi
20m 1s cthi:export-D82895451
cthi:export-D82895451
20m 1s
Use ATen API to get the device major arch FBGEMM_GPU-CPU Benchmark #5604: Pull request #4901 synchronize by cthi
20m 23s cthi:export-D82855103
cthi:export-D82855103
20m 23s
Use ATen API to get the device major arch FBGEMM_GPU-CPU Benchmark #5603: Pull request #4901 opened by cthi
20m 32s cthi:export-D82855103
cthi:export-D82855103
20m 32s
Save some binary size FBGEMM_GPU-CPU Benchmark #5602: Pull request #4900 opened by cthi
20m 34s cthi:export-D82842915
cthi:export-D82842915
20m 34s
Small changes to improve blackwell_fmha_test.py FBGEMM_GPU-CPU Benchmark #5601: Pull request #4896 synchronize by henrylhtsang
22m 11s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
22m 11s
Backward optimizations + rocm and gfx950 build support FBGEMM_GPU-CPU Benchmark #5600: Pull request #4729 synchronize by shbiswas834
17m 58s ROCm:shbiswas/uptream_develop_0815
ROCm:shbiswas/uptream_develop_0815
17m 58s
Add ability to pad the rowwise quantized tensors FBGEMM_GPU-CPU Benchmark #5599: Pull request #4877 synchronize by yyetim
20m 13s yyetim:export-D82486197
yyetim:export-D82486197
20m 13s
Migrate GenAI kv cache kernel arguments to use PTA_B FBGEMM_GPU-CPU Benchmark #5598: Pull request #4899 opened by q10
18m 19s q10:export-D82775043
q10:export-D82775043
18m 19s
Restrict to fp8, and patch 4.2.0 release changes FBGEMM_GPU-CPU Benchmark #5597: Pull request #4898 opened by henrylhtsang
18m 48s henrylhtsang:export-D82792657
henrylhtsang:export-D82792657
18m 48s
Add softmax_scale to blackwell cutlass fmha FBGEMM_GPU-CPU Benchmark #5596: Pull request #4897 opened by henrylhtsang
20m 0s henrylhtsang:export-D82788784
henrylhtsang:export-D82788784
20m 0s
Small changes to improve blackwell_fmha_test.py FBGEMM_GPU-CPU Benchmark #5595: Pull request #4896 synchronize by henrylhtsang
19m 59s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
19m 59s
Small changes to improve blackwell_fmha_test.py FBGEMM_GPU-CPU Benchmark #5594: Pull request #4896 synchronize by henrylhtsang
18s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
18s
Small changes to improve blackwell_fmha_test.py FBGEMM_GPU-CPU Benchmark #5593: Pull request #4896 opened by henrylhtsang
17m 27s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
17m 27s
Migrate GenAI kv cache kernels to FBGEMM_LAUNCH_KERNEL, pt 4 FBGEMM_GPU-CPU Benchmark #5592: Pull request #4895 opened by q10
20m 16s q10:export-D82773258
q10:export-D82773258
20m 16s
Migrate GenAI gqa attn splitk kernels to FBGEMM_LAUNCH_KERNEL, pt 1 FBGEMM_GPU-CPU Benchmark #5591: Pull request #4894 opened by q10
21m 30s q10:export-D81817544
q10:export-D81817544
21m 30s
upgrade cutlass to 4.2.0 for fbcode FBGEMM_GPU-CPU Benchmark #5590: Pull request #4893 opened by henrylhtsang
20m 57s henrylhtsang:export-D82567751
henrylhtsang:export-D82567751
20m 57s
Back out "Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100" FBGEMM_GPU-CPU Benchmark #5589: Pull request #4892 synchronize by jiawenliu64
19m 34s jiawenliu64:export-D82746070
jiawenliu64:export-D82746070
19m 34s