xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 02:15:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BUGFIX] GPTQ quantization compatibility for Qwen3 Next MOE models (AutoGPTQ and AutoRound-GPTQ) (#25268)

Browse Source 
Signed-off-by: JartX <sagformas@epdcenter.es>
This commit is contained in:
JartX 2025-09-20 05:18:13 +02:00 committed by GitHub
parent c308501cb6
commit 3642909617
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/models/qwen3_next.py
View File

@ -148,9 +148,11 @@ class Qwen3NextSparseMoeBlock(nn.Module):
def _maybe_ignore_quant_config(self, quant_config: QuantizationConfig):
# GPTQ configs do not have a list of ignored modules, however AutoGPTQ
# seems to avoid gate quantization.
# See: https://huggingface.co/Qwen/Qwen3-30B-A3B-GPTQ-Int4
if isinstance(quant_config, (GPTQConfig, GPTQMarlinConfig)):
# seems to avoid gate quantization while AutoRound does.
if isinstance(
quant_config,
(GPTQConfig,
GPTQMarlinConfig)) and not quant_config.autoround_version:
return None
return quant_config