Skip to content

Actions: pytorch/FBGEMM

FBGEMM_GPU-CUDA Benchmark

Actions

Loading...
Loading

Create status badge

Loading
217 workflow runs
217 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Improve Fused8BitRowwiseQuantizedSBFloatToFloatOrHalfNeon by 5%-15%
FBGEMM_GPU-CUDA Benchmark #218: Pull request #3860 opened by Nicoshev
March 21, 2025 15:07 1h 2m 8s Nicoshev:export-D71602944
March 21, 2025 15:07 1h 2m 8s
Add option to set build parallelism in OSS workflows
FBGEMM_GPU-CUDA Benchmark #217: Pull request #3859 synchronize by q10
March 20, 2025 23:56 59m 21s q10:export-D71571679
March 20, 2025 23:56 59m 21s
Add option to set build parallelism in OSS workflows
FBGEMM_GPU-CUDA Benchmark #216: Pull request #3859 opened by q10
March 20, 2025 23:28 29m 19s q10:export-D71571679
March 20, 2025 23:28 29m 19s
Revert "Use enum to select floating point format in FbgemmEmbedding APIs"
FBGEMM_GPU-CUDA Benchmark #215: Pull request #3858 opened by MatzeB
March 20, 2025 23:17 1h 1m 43s revert-3842-export-D68046358
March 20, 2025 23:17 1h 1m 43s
Back out "Replace LR access with wrapper"
FBGEMM_GPU-CUDA Benchmark #214: Pull request #3857 opened by spcyppt
March 20, 2025 21:25 1h 2m 55s spcyppt:export-D71578251
March 20, 2025 21:25 1h 2m 55s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #213: Pull request #3856 synchronize by q10
March 20, 2025 21:23 1h 0m 13s q10:export-D71350076
March 20, 2025 21:23 1h 0m 13s
Use enum to select floating point format in FbgemmEmbedding APIs
FBGEMM_GPU-CUDA Benchmark #212: Pull request #3842 synchronize by MatzeB
March 20, 2025 20:38 1h 2m 37s MatzeB:export-D68046358
March 20, 2025 20:38 1h 2m 37s
torch.ops.fbgemm.gather_scale_dense_tokens for oss.
FBGEMM_GPU-CUDA Benchmark #211: Pull request #3855 synchronize by levendlee
March 20, 2025 19:45 59m 9s levendlee:export-D71559646
March 20, 2025 19:45 59m 9s
torch.ops.fbgemm.gather_scale_dense_tokens for oss.
FBGEMM_GPU-CUDA Benchmark #210: Pull request #3855 synchronize by levendlee
March 20, 2025 19:32 13m 38s levendlee:export-D71559646
March 20, 2025 19:32 13m 38s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #209: Pull request #3856 synchronize by q10
March 20, 2025 19:19 59m 31s q10:export-D71350076
March 20, 2025 19:19 59m 31s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #208: Pull request #3856 synchronize by q10
March 20, 2025 19:15 4m 56s q10:export-D71350076
March 20, 2025 19:15 4m 56s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #207: Pull request #3856 synchronize by q10
March 20, 2025 19:13 3m 1s q10:export-D71350076
March 20, 2025 19:13 3m 1s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #206: Pull request #3856 synchronize by q10
March 20, 2025 19:08 6m 58s q10:export-D71350076
March 20, 2025 19:08 6m 58s
torch.ops.fbgemm.gather_scale_dense_tokens for oss.
FBGEMM_GPU-CUDA Benchmark #205: Pull request #3855 synchronize by levendlee
March 20, 2025 19:07 26m 4s levendlee:export-D71559646
March 20, 2025 19:07 26m 4s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #204: Pull request #3856 synchronize by q10
March 20, 2025 19:05 3m 2s q10:export-D71350076
March 20, 2025 19:05 3m 2s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #203: Pull request #3856 synchronize by q10
March 20, 2025 19:05 11s q10:export-D71350076
March 20, 2025 19:05 11s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #202: Pull request #3856 synchronize by q10
March 20, 2025 19:04 53s q10:export-D71350076
March 20, 2025 19:04 53s
torch.ops.fbgemm.gather_scale_dense_tokens for oss.
FBGEMM_GPU-CUDA Benchmark #201: Pull request #3855 synchronize by levendlee
March 20, 2025 18:59 8m 37s levendlee:export-D71559646
March 20, 2025 18:59 8m 37s
torch.ops.fbgemm.gather_scale_dense_tokens for oss.
FBGEMM_GPU-CUDA Benchmark #200: Pull request #3855 synchronize by levendlee
March 20, 2025 18:25 35m 14s levendlee:export-D71559646
March 20, 2025 18:25 35m 14s
Add abstractions for writing out data (flesh out D71147675, pt 1)
FBGEMM_GPU-CUDA Benchmark #199: Pull request #3856 opened by q10
March 20, 2025 18:12 52m 15s q10:export-D71350076
March 20, 2025 18:12 52m 15s
torch.ops.fbgemm.gather_scale_dense_tokens for oss.
FBGEMM_GPU-CUDA Benchmark #198: Pull request #3855 opened by levendlee
March 20, 2025 17:55 30m 45s levendlee:export-D71559646
March 20, 2025 17:55 30m 45s
F8I4 Grouped Gemm Optimization for Sparse M
FBGEMM_GPU-CUDA Benchmark #197: Pull request #3854 synchronize by jwfromm
March 20, 2025 16:44 1h 2m 20s jwfromm:export-D71510967
March 20, 2025 16:44 1h 2m 20s
Unifying TBE API using List (Frontend) - reland
FBGEMM_GPU-CUDA Benchmark #196: Pull request #3821 synchronize by spcyppt
March 20, 2025 16:26 59m 22s spcyppt:export-D71010630
March 20, 2025 16:26 59m 22s
Unifying TBE API using List (Frontend) - reland
FBGEMM_GPU-CUDA Benchmark #195: Pull request #3821 synchronize by spcyppt
March 20, 2025 00:04 59m 0s spcyppt:export-D71010630
March 20, 2025 00:04 59m 0s