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 15, 21:00 UTC
Small update for external_launcher backend docs (#14288)
Zhe Zhang committed
Mar 5, 2025 at 05:30 UTC
47d4a7e00400c4de74a7cf565b21a23f9e660ab4
1 file changed
+1
vllm/executor/uniproc_executor.py
+1
@@ -103,6 +103,7 @@ class ExecutorWithExternalLauncher(UniProcExecutor):
103
# so we can use the env:// method.
104
# required env vars:
105
# - RANK
106
+ # - LOCAL_RANK
107
# - MASTER_ADDR
108
# - MASTER_PORT
109
distributed_init_method = "env://"