biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 Deprecation] Remove async_output_proc, preemption mode, delay factor (#25334)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-09-21 08:52:32 -07:00
committed by GitHub
parent 26e673fe93
commit 0ff8ebb2d7
15 changed files with 12 additions and 210 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/llm.py
View File

@@ -137,8 +137,6 @@ class LLM:
back to the eager mode.
disable_custom_all_reduce: See
[ParallelConfig][vllm.config.ParallelConfig].
disable_async_output_proc: Disable async output processing.
This may result in lower performance.
hf_token: The token to use as HTTP bearer authorization for remote files
. If `True`, will use the token generated when running
`huggingface-cli login` (stored in `~/.huggingface`).
@@ -188,7 +186,6 @@ class LLM:
enforce_eager: bool = False,
max_seq_len_to_capture: int = 8192,
disable_custom_all_reduce: bool = False,
disable_async_output_proc: bool = False,
hf_token: Optional[Union[bool, str]] = None,
hf_overrides: Optional[HfOverrides] = None,
mm_processor_kwargs: Optional[dict[str, Any]] = None,
@@ -286,7 +283,6 @@ class LLM:
enforce_eager=enforce_eager,
max_seq_len_to_capture=max_seq_len_to_capture,
disable_custom_all_reduce=disable_custom_all_reduce,
disable_async_output_proc=disable_async_output_proc,
hf_token=hf_token,
hf_overrides=hf_overrides,
mm_processor_kwargs=mm_processor_kwargs,