mirror of
https://github.com/bentoml/OpenLLM.git
synced 2026-02-01 11:22:15 -05:00
fix(llm): remove unecessary parsing
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
@@ -184,8 +184,8 @@ class LLM(t.Generic[M, T]):
|
||||
adapter_map=convert_peft_config_type(adapter_map) if adapter_map is not None else None,
|
||||
serialisation=serialisation,
|
||||
local=_local,
|
||||
max_model_len=getenv('max_model_len', default=max_model_len),
|
||||
gpu_memory_utilization=getenv('gpu_memory_utilization', default=gpu_memory_utilization),
|
||||
max_model_len=max_model_len,
|
||||
gpu_memory_utilization=gpu_memory_utilization,
|
||||
LLM__model_attrs=model_attrs,
|
||||
LLM__tokenizer_attrs=tokenizer_attrs,
|
||||
llm_dtype__=dtype.lower(),
|
||||
|
||||
Reference in New Issue
Block a user