[ROCm][FEAT] Integrate aiter gemm w8a8 ptpc (#33773)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
@@ -397,8 +397,6 @@ class Fp8LinearMethod(LinearMethodBase):
|
||||
if self.block_quant:
|
||||
assert not self.act_q_static
|
||||
|
||||
self.fp8_linear.process_weights_after_loading(layer)
|
||||
|
||||
# If checkpoint not serialized fp8, quantize the weights.
|
||||
else:
|
||||
# If checkpoint is fp8 per-tensor, handle that there are N scales for N
|
||||
@@ -428,6 +426,8 @@ class Fp8LinearMethod(LinearMethodBase):
|
||||
else:
|
||||
layer.input_scale = None
|
||||
|
||||
self.fp8_linear.process_weights_after_loading(layer)
|
||||
|
||||
def apply(
|
||||
self,
|
||||
layer: torch.nn.Module,
|
||||
|
||||
Reference in New Issue
Block a user