[Feat][BugFix]Support the Qwen3-Next-80B-A3B-Instruct quantization model&Fix the NZ issue (#4245)
### What this PR does / why we need it?
Support the Qwen3-Next-80B-A3B-Instruct quantization model and Fix the
NZ issue. Triton kernel doesn't support data format nz, thus we skip
converting weight to nz on layer `conv1d`
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: IncSec <1790766300@qq.com>
This commit is contained in:
@@ -222,6 +222,8 @@ packed_modules_model_mapping = {
|
||||
],
|
||||
"gate_up_proj": ["gate_proj", "up_proj"],
|
||||
"in_proj": ["in_proj_qkvz", "in_proj_ba"],
|
||||
"experts":
|
||||
["experts.0.gate_proj", "experts.0.up_proj", "experts.0.down_proj"]
|
||||
},
|
||||
"qwen2_5_vl": {
|
||||
"qkv_proj": [
|
||||
|
||||
Reference in New Issue
Block a user