fix: resolve the fp8 bug introduced by vLLM 0.5.5

sgl-project · Aug 31, 2024 · d2050a2 · d2050a2
1 parent 51c554d
commit d2050a2
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/python/sglang/srt/models/deepseek_v2.py b/python/sglang/srt/models/deepseek_v2.py
@@ -695,7 +695,7 @@ def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
                     weight_loader(
                         param,
                         loaded_weight,
-                        weight_name,
+                        name,
                         shard_id=shard_id,
                         expert_id=expert_id,
                     )