initial mod implementation

This commit is contained in:
Eugene Rakhmatulin
2025-12-23 13:38:10 -08:00
parent a9b1bb5947
commit 19dec79c5c
3 changed files with 174 additions and 17 deletions

View File

@@ -0,0 +1,18 @@
--- a/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/glm4_moe.py
+++ b/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/glm4_moe.py
@@ -537,6 +537,7 @@
if is_pp_missing_parameter(name, self):
continue
+ if ('k_scale' in name or 'v_scale' in name) and name not in params_dict: continue
param = params_dict[name]
weight_loader = param.weight_loader
weight_loader(param, loaded_weight, shard_id)
@@ -596,6 +597,7 @@
if is_pp_missing_parameter(name, self):
continue
+ if ('k_scale' in name or 'v_scale' in name) and name not in params_dict: continue
param = params_dict[name]
weight_loader = getattr(
param, "weight_loader", default_weight_loader

View File

@@ -0,0 +1,3 @@
#!/bin/bash
set -e
patch -p1 -d / < glm4_moe.patch