mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-05-03 13:22:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(gpus): disable slots for now to enable cached_property

Browse Source 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron
2023-11-26 02:49:48 -05:00
parent 21bf26583d
commit 43a96dab2c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
openllm-python/src/openllm/_llm.py
View File

@@ -45,7 +45,7 @@ _AdapterTuple: type[AdapterTuple] = codegen.make_attr_tuple_class('AdapterTuple'
ResolvedAdapterMap = t.Dict[AdapterType, t.Dict[str, t.Tuple['PeftConfig', str]]]
@attr.define(slots=True, repr=False, init=False)
@attr.define(slots=False, repr=False, init=False)
class LLM(t.Generic[M, T]):
async def generate(
self, prompt, prompt_token_ids=None, stop=None, stop_token_ids=None, request_id=None, adapter_name=None, **attrs