[ROCm][FEAT] Integrate aiter gemm w8a8 ptpc (#33773)

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm
2026-04-16 09:55:29 +08:00
committed by GitHub
parent 343f65234b
commit 5f7fab881a
9 changed files with 279 additions and 23 deletions
@@ -175,6 +175,8 @@ class FBGEMMFp8LinearMethod(LinearMethodBase):
# Activations not quantized for marlin.
del layer.input_scale_ub
self.fp8_linear.process_weights_after_loading(layer)
def apply(
self,
layer: torch.nn.Module,