A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 13, 03:15 UTC
[Model] Fix lmhead init bug of bailing_moe (#28777)
Signed-off-by: hwhaokun <haokun0405@163.com> Co-authored-by: zhaozx-cn <zhaozx2116@163.com> Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
hwhaokun committed
Nov 15, 2025 at 21:44 UTC
085a5253321a66d7aac0f990d82417ad85ec0eb0
1 file changed
+1
-1
vllm/model_executor/models/bailing_moe.py
+1
-1
@@ -599,7 +599,7 @@ class BailingMoeForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
599
config.vocab_size,
600
config.hidden_size,
601
quant_config=quant_config,
602
- prefix=f"{prefix}.lm_head",
602
+ prefix=maybe_prefix(prefix, "lm_head"),
603
)
604
self.logits_processor = LogitsProcessor(config.vocab_size)
605
else: