saymrwulf/transformers
1
0
Fork 0
mirror of https://github.com/saymrwulf/transformers.git synced 2026-05-14 20:58:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update

Browse source
This commit is contained in:
MekkCyber 2025-02-08 14:37:19 +00:00
parent 68a3234aa8
commit d41e11b3f1
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/transformers/integrations/fp8.py
View file

@ -56,7 +56,7 @@ def act_quant(x: torch.Tensor, block_size: int = 128) -> Tuple[torch.Tensor, tor
act_quant_kernel[grid](x, y, s, BLOCK_SIZE=block_size)
return y, s
# Adapted from https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/layers/quantization/fp8_kernel.py
@triton.jit
def _w8a8_block_fp8_matmul(
# Pointers to inputs and output