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
5,015 workflow runs
5,015 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

more hipify v2 fixes (#4854) FBGEMM_GPU-CPU Benchmark #5657: Pull request #4921 synchronize by q10
23m 42s q10:export-D82186865
q10:export-D82186865
23m 42s
more hipify v2 fixes (#4854) FBGEMM_GPU-CPU Benchmark #5656: Pull request #4921 synchronize by q10
13m 52s q10:export-D82186865
q10:export-D82186865
13m 52s
more hipify v2 fixes (#4854) FBGEMM_GPU-CPU Benchmark #5655: Pull request #4921 synchronize by q10
9m 41s q10:export-D82186865
q10:export-D82186865
9m 41s
more hipify v2 fixes (#4854) FBGEMM_GPU-CPU Benchmark #5654: Pull request #4921 opened by q10
10m 29s q10:export-D82186865
q10:export-D82186865
10m 29s
Demonstration of per-op targets FBGEMM_GPU-CPU Benchmark #5653: Pull request #4919 synchronize by cthi
25m 22s cthi:export-D83056686
cthi:export-D83056686
25m 22s
add one mode in Rowwise_adagrad_with_counter FBGEMM_GPU-CPU Benchmark #5652: Pull request #4920 opened by dudongsu
Action required dudongsu:export-D82576034
dudongsu:export-D82576034
Action required
Demonstration of per-op targets FBGEMM_GPU-CPU Benchmark #5651: Pull request #4919 synchronize by cthi
7m 47s cthi:export-D83056686
cthi:export-D83056686
7m 47s
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU-CPU Benchmark #5650: Pull request #4891 synchronize by jiawenliu64
21m 30s export-D82700455
export-D82700455
21m 30s
Demonstration of per-op targets FBGEMM_GPU-CPU Benchmark #5649: Pull request #4919 opened by cthi
15m 21s cthi:export-D83056686
cthi:export-D83056686
15m 21s
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU-CPU Benchmark #5648: Pull request #4891 synchronize by jiawenliu64
13m 50s export-D82700455
export-D82700455
13m 50s
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU-CPU Benchmark #5647: Pull request #4891 synchronize by jiawenliu64
10m 22s export-D82700455
export-D82700455
10m 22s
Support multiple total-k and total-m in quantize bench FBGEMM_GPU-CPU Benchmark #5646: Pull request #4890 synchronize by jiawenliu64
26m 25s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
26m 25s
Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 (resubmit) FBGEMM_GPU-CPU Benchmark #5645: Pull request #4913 synchronize by jiawenliu64
21m 34s jiawenliu64:export-D83001505
jiawenliu64:export-D83001505
21m 34s
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU-CPU Benchmark #5644: Pull request #4891 synchronize by jiawenliu64
6m 54s export-D82700455
export-D82700455
6m 54s
Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 (resubmit) FBGEMM_GPU-CPU Benchmark #5643: Pull request #4913 synchronize by jiawenliu64
7m 4s jiawenliu64:export-D83001505
jiawenliu64:export-D83001505
7m 4s
Support multiple total-k and total-m in quantize bench FBGEMM_GPU-CPU Benchmark #5642: Pull request #4890 synchronize by jiawenliu64
9m 49s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
9m 49s
Fix clang-tidy and nvcc warnings FBGEMM_GPU-CPU Benchmark #5641: Pull request #4918 opened by cyyever
23m 31s cyyever:tidy_code3
cyyever:tidy_code3
23m 31s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU-CPU Benchmark #5640: Pull request #4912 synchronize by seanx92
19m 50s seanx92:export-D82507938
seanx92:export-D82507938
19m 50s
avx512 based int8 -> bf16 dequantization FBGEMM_GPU-CPU Benchmark #5639: Pull request #4912 synchronize by seanx92
20m 25s seanx92:export-D82507938
seanx92:export-D82507938
20m 25s
Disable SWA related decode kernel tests since they are not supported FBGEMM_GPU-CPU Benchmark #5638: Pull request #4911 synchronize by Alkaid-Benetnash
19m 22s Alkaid-Benetnash:export-D82991496
Alkaid-Benetnash:export-D82991496
19m 22s
Add cutlass decode kernel to TritonBench FBGEMM_GPU-CPU Benchmark #5636: Pull request #4853 synchronize by Aya-ZIbra
19m 15s Aya-ZIbra:export-D80041532
Aya-ZIbra:export-D80041532
19m 15s
Support bf16 in blackwell cutlass decode attention kernel FBGEMM_GPU-CPU Benchmark #5635: Pull request #4916 opened by Aya-ZIbra
Action required Aya-ZIbra:export-D82991495
Aya-ZIbra:export-D82991495
Action required
Optimize wgrad CUTLASS grouped gemm FBGEMM_GPU-CPU Benchmark #5634: Pull request #4891 synchronize by jiawenliu64
19m 0s export-D82700455
export-D82700455
19m 0s
Support multiple total-k and total-m in quantize bench FBGEMM_GPU-CPU Benchmark #5633: Pull request #4890 synchronize by jiawenliu64
20m 7s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
20m 7s
Support multiple total-k and total-m in quantize bench FBGEMM_GPU-CPU Benchmark #5632: Pull request #4890 synchronize by jiawenliu64
9m 57s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
9m 57s