Skip to content

Actions: pytorch/FBGEMM

Actions

Build FBGEMM GenAI x86 Linux Wheels

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build_wheels_genai_linux_x86.yml
5,586 workflow runs
5,586 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add ability to pad the rowwise quantized tensors (#4877) Build FBGEMM GenAI x86 Linux Wheels #6018: Commit ac8ac3e pushed by facebook-github-bot
2h 25m 33s main
main
2h 25m 33s
Save some binary size Build FBGEMM GenAI x86 Linux Wheels #6017: Pull request #4900 opened by cthi
2h 21m 49s cthi:export-D82842915
cthi:export-D82842915
2h 21m 49s
Small changes to improve blackwell_fmha_test.py Build FBGEMM GenAI x86 Linux Wheels #6016: Pull request #4896 synchronize by henrylhtsang
2h 19m 35s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
2h 19m 35s
Add softmax_scale to blackwell cutlass fmha (#4897) Build FBGEMM GenAI x86 Linux Wheels #6015: Commit f82e3b2 pushed by facebook-github-bot
2h 25m 32s main
main
2h 25m 32s
Backward optimizations + rocm and gfx950 build support Build FBGEMM GenAI x86 Linux Wheels #6014: Pull request #4729 synchronize by shbiswas834
2h 14m 56s ROCm:shbiswas/uptream_develop_0815
ROCm:shbiswas/uptream_develop_0815
2h 14m 56s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #6013: Pull request #4877 synchronize by yyetim
2h 16m 32s yyetim:export-D82486197
yyetim:export-D82486197
2h 16m 32s
Restrict to fp8, and patch 4.2.0 release changes (#4898) Build FBGEMM GenAI x86 Linux Wheels #6012: Commit 1e80f1a pushed by facebook-github-bot
51m 55s main
main
51m 55s
2025-09-19 nightly release (9b66962e7099846120bbf912114782d23a9ee4bf) Build FBGEMM GenAI x86 Linux Wheels #6011: Commit 3cea487 pushed by pytorchbot
2h 22m 7s nightly
nightly
2h 22m 7s
Migrate GenAI kv cache kernel arguments to use PTA_B (#4899) Build FBGEMM GenAI x86 Linux Wheels #6010: Commit 9b66962 pushed by facebook-github-bot
2h 22m 46s main
main
2h 22m 46s
add blog link (#4888) Build FBGEMM GenAI x86 Linux Wheels #6009: Commit e6d8742 pushed by facebook-github-bot
2h 30m 13s main
main
2h 30m 13s
Migrate GenAI kv cache kernel arguments to use PTA_B Build FBGEMM GenAI x86 Linux Wheels #6008: Pull request #4899 opened by q10
2h 21m 18s q10:export-D82775043
q10:export-D82775043
2h 21m 18s
Migrate GenAI kv cache kernels to FBGEMM_LAUNCH_KERNEL, pt 4 (#4895) Build FBGEMM GenAI x86 Linux Wheels #6007: Commit 944647a pushed by facebook-github-bot
22m 21s main
main
22m 21s
Restrict to fp8, and patch 4.2.0 release changes Build FBGEMM GenAI x86 Linux Wheels #6006: Pull request #4898 opened by henrylhtsang
2h 16m 6s henrylhtsang:export-D82792657
henrylhtsang:export-D82792657
2h 16m 6s
Add softmax_scale to blackwell cutlass fmha Build FBGEMM GenAI x86 Linux Wheels #6005: Pull request #4897 opened by henrylhtsang
2h 17m 33s henrylhtsang:export-D82788784
henrylhtsang:export-D82788784
2h 17m 33s
Small changes to improve blackwell_fmha_test.py Build FBGEMM GenAI x86 Linux Wheels #6004: Pull request #4896 synchronize by henrylhtsang
2h 48m 2s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
2h 48m 2s
Small changes to improve blackwell_fmha_test.py Build FBGEMM GenAI x86 Linux Wheels #6003: Pull request #4896 synchronize by henrylhtsang
19s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
19s
Small changes to improve blackwell_fmha_test.py Build FBGEMM GenAI x86 Linux Wheels #6002: Pull request #4896 opened by henrylhtsang
17m 57s henrylhtsang:export-D81992869
henrylhtsang:export-D81992869
17m 57s
Migrate GenAI kv cache kernels to FBGEMM_LAUNCH_KERNEL, pt 4 Build FBGEMM GenAI x86 Linux Wheels #6001: Pull request #4895 opened by q10
2h 17m 28s q10:export-D82773258
q10:export-D82773258
2h 17m 28s
Migrate GenAI gqa attn splitk kernels to FBGEMM_LAUNCH_KERNEL, pt 1 Build FBGEMM GenAI x86 Linux Wheels #6000: Pull request #4894 opened by q10
2h 14m 57s q10:export-D81817544
q10:export-D81817544
2h 14m 57s
Back out "Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 … Build FBGEMM GenAI x86 Linux Wheels #5999: Commit 53f9e51 pushed by facebook-github-bot
2h 33m 28s main
main
2h 33m 28s
upgrade cutlass to 4.2.0 for fbcode Build FBGEMM GenAI x86 Linux Wheels #5998: Pull request #4893 opened by henrylhtsang
2h 30m 32s henrylhtsang:export-D82567751
henrylhtsang:export-D82567751
2h 30m 32s
Back out "Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100" Build FBGEMM GenAI x86 Linux Wheels #5997: Pull request #4892 synchronize by jiawenliu64
2h 19m 12s jiawenliu64:export-D82746070
jiawenliu64:export-D82746070
2h 19m 12s
Back out "Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100" Build FBGEMM GenAI x86 Linux Wheels #5996: Pull request #4892 opened by jiawenliu64
11m 29s jiawenliu64:export-D82746070
jiawenliu64:export-D82746070
11m 29s
add blog link Build FBGEMM GenAI x86 Linux Wheels #5995: Pull request #4888 synchronize by sijiac
2h 28m 44s sijiac:export-D82681043
sijiac:export-D82681043
2h 28m 44s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5994: Pull request #4877 synchronize by yyetim
2h 28m 11s yyetim:export-D82486197
yyetim:export-D82486197
2h 28m 11s