[Docs] add runai_streamer_sharded to LoadConfig (#27937)

Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-11-04 04:35:16 +08:00
parent 145c00a4d3
commit 786030721e
1 changed files with 2 additions and 0 deletions
--- a/vllm/config/load.py
+++ b/vllm/config/load.py
@@ -40,6 +40,8 @@ class LoadConfig:
    more information.\n
    - "runai_streamer" will load the Safetensors weights using Run:ai Model
    Streamer.\n
+    - "runai_streamer_sharded" will load weights from pre-sharded checkpoint
+    files using Run:ai Model Streamer.\n
    - "bitsandbytes" will load the weights using bitsandbytes quantization.\n
    - "sharded_state" will load weights from pre-sharded checkpoint files,
    supporting efficient loading of tensor-parallel models.\n