x
This commit is contained in:
@@ -110,6 +110,7 @@ def resolve_model_profile(
|
||||
"served_model_name": profile.get("served_model_name", model_key),
|
||||
"dtype": _to_str(profile.get("dtype")),
|
||||
"quantization": _to_str(profile.get("quantization")),
|
||||
"model_impl": _to_str(profile.get("model_impl")),
|
||||
"reasoning_parser": _to_str(profile.get("reasoning_parser")),
|
||||
"max_model_len": _to_int(profile.get("ctx"), 8192),
|
||||
"max_num_seqs": _to_int(profile.get("max_num_seqs"), 64),
|
||||
|
||||
Reference in New Issue
Block a user