xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 21:05:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove GLM-4.5 quantization wrong Code (#21435)

Browse Source
This commit is contained in:
Yuxuan Zhang 2025-07-24 16:52:43 +08:00 committed by GitHub
parent 610852a423
commit 85bda9e7d0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py
View File

@ -20,7 +20,7 @@ from vllm.transformers_utils.tokenizer import AnyTokenizer
logger = init_logger(__name__) logger = init_logger(__name__)
@ToolParserManager.register_module("glm4_moe") @ToolParserManager.register_module("glm45")
class Glm4MoeModelToolParser(ToolParser): class Glm4MoeModelToolParser(ToolParser):
def __init__(self, tokenizer: AnyTokenizer): def __init__(self, tokenizer: AnyTokenizer):

1
vllm/model_executor/models/glm4_moe.py
View File

@ -390,7 +390,6 @@ class Glm4MoeModel(nn.Module):
self.embed_tokens = VocabParallelEmbedding( self.embed_tokens = VocabParallelEmbedding(
config.vocab_size, config.vocab_size,
config.hidden_size, config.hidden_size,
quant_config=quant_config,
prefix=f"{prefix}.embed_tokens") prefix=f"{prefix}.embed_tokens")
else: else:
self.embed_tokens = PPMissingLayer() self.embed_tokens = PPMissingLayer()

2
vllm/reasoning/glm4_moe_reasoning_parser.py
View File

@ -14,7 +14,7 @@ from vllm.reasoning import ReasoningParser, ReasoningParserManager
logger = init_logger(__name__) logger = init_logger(__name__)
@ReasoningParserManager.register_module("glm4_moe") @ReasoningParserManager.register_module("glm45")
class Glm4MoeModelReasoningParser(ReasoningParser): class Glm4MoeModelReasoningParser(ReasoningParser):
""" """
Reasoning parser for the Glm4MoeModel model. Reasoning parser for the Glm4MoeModel model.