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

[Refactor] Separate sequence and token pooling types (#32026)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-10 12:53:24 +08:00
committed by GitHub
parent 52d428295d
commit 583a90e005
42 changed files with 324 additions and 204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/tasks.py
View File

@@ -3,11 +3,11 @@
from typing import Literal, get_args
GenerationTask = Literal["generate", "transcription"]
GENERATION_TASKS = get_args(GenerationTask)
GENERATION_TASKS: tuple[GenerationTask, ...] = get_args(GenerationTask)
PoolingTask = Literal[
"embed", "classify", "score", "token_embed", "token_classify", "plugin"
]
POOLING_TASKS = get_args(PoolingTask)
POOLING_TASKS: tuple[PoolingTask, ...] = get_args(PoolingTask)
SupportedTask = Literal[GenerationTask, PoolingTask]