biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Tidy up some spec decode logic in GPUModelRunner (#31591)

Browse Source 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Nick Hill
2026-01-08 09:10:07 -08:00
committed by GitHub
parent 49568d5cf9
commit a3d909ad2b
3 changed files with 51 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/gpu_worker.py
View File

@@ -390,7 +390,7 @@ class Worker(WorkerBase):
"""
self.model_config.max_model_len = max_model_len
if self.model_runner is not None:
self.model_runner.max_model_len = max_model_len
self.model_runner.update_max_model_len(max_model_len)
logger.debug("Updated max_model_len to %d", max_model_len)
def initialize_from_config(self, kv_cache_config: KVCacheConfig) -> None: