Skip to content

GitLab

Unverified Commit ca0d9222 authored by Michael Goin's avatar Michael Goin Committed by GitHub
Browse files

[Bugfix] Fix compressed_tensors_moe bad config.strategy (#9677)

parent 9645b9f6
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
View file @ ca0d9222
...@@ -245,7 +245,7 @@ class CompressedTensorsWNA16MoEMethod(CompressedTensorsMoEMethod): ...@@ -245,7 +245,7 @@ class CompressedTensorsWNA16MoEMethod(CompressedTensorsMoEMethod):
config = self.quant_config.target_scheme_map["Linear"].get("weights") config = self.quant_config.target_scheme_map["Linear"].get("weights")
self.num_bits = config.num_bits self.num_bits = config.num_bits
self.packed_factor = 32 // config.num_bits self.packed_factor = 32 // config.num_bits
self.strategy = config.strategy.value self.strategy = config.strategy
self.group_size = config.group_size self.group_size = config.group_size
assert config.symmetric, ( assert config.symmetric, (
"Only symmetric quantization is supported for MoE") "Only symmetric quantization is supported for MoE")
......
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