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
5,593 workflow runs
5,593 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

dequantize_fp8_cache_kernel: Move D=128 device-side-assertion check to host Build FBGEMM GenAI x86 Linux Wheels #5993: Pull request #4869 synchronize by ColinPeppler
2h 28m 29s ColinPeppler:export-D82320518
ColinPeppler:export-D82320518
2h 28m 29s
dequantize_fp8_cache_kernel: Move D=128 device-side-assertion check to host Build FBGEMM GenAI x86 Linux Wheels #5992: Pull request #4869 synchronize by ColinPeppler
19s ColinPeppler:export-D82320518
ColinPeppler:export-D82320518
19s
symmetric quantization to FBGEMM prefill token-wise FP8 (fixed) Build FBGEMM GenAI x86 Linux Wheels #5991: Pull request #4868 synchronize by ColinPeppler
2h 29m 1s ColinPeppler:export-D82320500
ColinPeppler:export-D82320500
2h 29m 1s
fix the scaled input issue Build FBGEMM GenAI x86 Linux Wheels #5990: Pull request #4884 synchronize by pyjhzwh
2h 29m 56s pyjhzwh:export-D82147819
pyjhzwh:export-D82147819
2h 29m 56s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5989: Pull request #4877 synchronize by yyetim
20m 3s yyetim:export-D82486197
yyetim:export-D82486197
20m 3s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5988: Pull request #4877 synchronize by yyetim
7m 42s yyetim:export-D82486197
yyetim:export-D82486197
7m 42s
Backward optimizations + rocm and gfx950 build support Build FBGEMM GenAI x86 Linux Wheels #5987: Pull request #4729 synchronize by liligwu
Action required ROCm:shbiswas/uptream_develop_0815
ROCm:shbiswas/uptream_develop_0815
Action required
2025-09-18 nightly release (fd32631d837b41251311099c393af7d7be5cfbf5) Build FBGEMM GenAI x86 Linux Wheels #5986: Commit 5206781 pushed by pytorchbot
2h 33m 26s nightly
nightly
2h 33m 26s
Optimize wgrad CUTLASS grouped gemm Build FBGEMM GenAI x86 Linux Wheels #5985: Pull request #4891 opened by jiawenliu64
2h 35m 25s export-D82700455
export-D82700455
2h 35m 25s
Support multiple total-k and total-m in quantize bench Build FBGEMM GenAI x86 Linux Wheels #5984: Pull request #4890 opened by jiawenliu64
2h 28m 55s jiawenliu64:export-D82700396
jiawenliu64:export-D82700396
2h 28m 55s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5983: Pull request #4877 synchronize by yyetim
2h 31m 10s yyetim:export-D82486197
yyetim:export-D82486197
2h 31m 10s
fix the scaled input issue Build FBGEMM GenAI x86 Linux Wheels #5982: Pull request #4884 synchronize by pyjhzwh
2h 31m 11s pyjhzwh:export-D82147819
pyjhzwh:export-D82147819
2h 31m 11s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5981: Pull request #4877 synchronize by yyetim
56m 56s yyetim:export-D82486197
yyetim:export-D82486197
56m 56s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5980: Pull request #4877 synchronize by yyetim
Action required yyetim:export-D82486197
yyetim:export-D82486197
Action required
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5979: Pull request #4877 synchronize by yyetim
Action required yyetim:export-D82486197
yyetim:export-D82486197
Action required
Migrate GenAI kv cache kernel arguments to use PTA_B (#4887) Build FBGEMM GenAI x86 Linux Wheels #5978: Commit fd32631 pushed by facebook-github-bot
2h 36m 52s main
main
2h 36m 52s
fix the scaled input issue Build FBGEMM GenAI x86 Linux Wheels #5977: Pull request #4884 synchronize by pyjhzwh
40m 35s pyjhzwh:export-D82147819
pyjhzwh:export-D82147819
40m 35s
fix the scaled input issue Build FBGEMM GenAI x86 Linux Wheels #5976: Pull request #4884 synchronize by pyjhzwh
Action required pyjhzwh:export-D82147819
pyjhzwh:export-D82147819
Action required
fix the scaled input issue Build FBGEMM GenAI x86 Linux Wheels #5975: Pull request #4884 synchronize by pyjhzwh
Action required pyjhzwh:export-D82147819
pyjhzwh:export-D82147819
Action required
MI350X FP8 triton patch Build FBGEMM GenAI x86 Linux Wheels #5974: Pull request #4889 opened by JChunX
2h 27m 21s JChunX:export-D81180838
JChunX:export-D81180838
2h 27m 21s
add blog link Build FBGEMM GenAI x86 Linux Wheels #5973: Pull request #4888 opened by sijiac
2h 30m 57s sijiac:export-D82681043
sijiac:export-D82681043
2h 30m 57s
Add ability to pad the rowwise quantized tensors Build FBGEMM GenAI x86 Linux Wheels #5972: Pull request #4877 synchronize by yyetim
1h 27m 58s yyetim:export-D82486197
yyetim:export-D82486197
1h 27m 58s
Migrate GenAI kv cache kernel arguments to use PTA_B Build FBGEMM GenAI x86 Linux Wheels #5971: Pull request #4887 opened by q10
2h 34m 28s q10:export-D81703942
q10:export-D81703942
2h 34m 28s
Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 (… Build FBGEMM GenAI x86 Linux Wheels #5970: Commit 57c2293 pushed by facebook-github-bot
2h 39m 52s main
main
2h 39m 52s
Migrate GenAI kv cache kernels to FBGEMM_LAUNCH_KERNEL, pt 3 (#4885) Build FBGEMM GenAI x86 Linux Wheels #5969: Commit ff8b5b0 pushed by facebook-github-bot
26m 55s main
main
26m 55s