Skip to content

GitLab

Commit 07c69390 authored by zhuwenwen's avatar zhuwenwen
Browse files

Update qwen3_moe.py

parent 90e10dee
Show whitespace changes
Inline Side-by-side
Showing with 4 additions and 4 deletions
vllm/model_executor/models/qwen3_moe.py
View file @ 07c69390
...@@ -332,9 +332,9 @@ class Qwen3MoeModel(nn.Module): ...@@ -332,9 +332,9 @@ class Qwen3MoeModel(nn.Module):
self.padding_idx = config.pad_token_id self.padding_idx = config.pad_token_id
self.vocab_size = config.vocab_size self.vocab_size = config.vocab_size
self.config = config self.config = config
if self.config.quantization_config["bits"] == 4: # if self.config.quantization_config["bits"] == 4:
os.environ['LLAMA_NN'] = '0' # os.environ['LLAMA_NN'] = '0'
os.environ['LM_NN'] = '0' # os.environ['LM_NN'] = '0'
self.embed_tokens = VocabParallelEmbedding( self.embed_tokens = VocabParallelEmbedding(
config.vocab_size, config.vocab_size,
config.hidden_size, config.hidden_size,
......
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