fix typo quantization (#2469)

asaiacai · web-flow · commit faca3a31806c · 2023-09-28T20:01:16.000-07:00
diff --git a/fastchat/serve/vllm_worker.py b/fastchat/serve/vllm_worker.py
@@ -192,6 +192,7 @@ async def api_model_details(request: Request):
         "--controller-address", type=str, default="http://localhost:21001"
     )
     parser.add_argument("--model-path", type=str, default="lmsys/vicuna-7b-v1.3")
+    parser.add_argument("--quantization", type=str)
     parser.add_argument(
         "--model-names",
         type=lambda s: s.split(","),

Original file line number	Diff line number	Diff line change
`@@ -192,6 +192,7 @@ async def api_model_details(request: Request):`
`192`	`192`	`"--controller-address", type=str, default="http://localhost:21001"`
`193`	`193`	`)`
`194`	`194`	`parser.add_argument("--model-path", type=str, default="lmsys/vicuna-7b-v1.3")`
	`195`	`+ parser.add_argument("--quantization", type=str)`
`195`	`196`	`parser.add_argument(`
`196`	`197`	`"--model-names",`
`197`	`198`	`type=lambda s: s.split(","),`