Skip to content

GitLab

Unverified Commit 9fac6aa3 authored by Lucas Wilkinson's avatar Lucas Wilkinson Committed by GitHub
Browse files

[BugFix] Fix DeepGEMM warmup, no m.weight_scale_inv (#25206) 


Signed-off-by: default avatarLucas Wilkinson <lwilkins@redhat.com>
parent a53ad626
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/warmup/deep_gemm_warmup.py
View file @ 9fac6aa3
...@@ -36,7 +36,7 @@ def _extract_data_from_linear_base_module( ...@@ -36,7 +36,7 @@ def _extract_data_from_linear_base_module(
assert m.quant_method.quant_config is not None assert m.quant_method.quant_config is not None
w = m.weight w = m.weight
ws = m.weight_scale_inv ws = m.weight_scale
quant_block_size = m.quant_method.quant_config.weight_block_size quant_block_size = m.quant_method.quant_config.weight_block_size
assert isinstance(w, torch.Tensor) assert isinstance(w, torch.Tensor)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment