Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
23 lines
888 B
Python
23 lines
888 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
from typing import Literal, get_args
|
|
|
|
GenerationTask = Literal["generate", "transcription", "realtime"]
|
|
GENERATION_TASKS: tuple[GenerationTask, ...] = get_args(GenerationTask)
|
|
|
|
PoolingTask = Literal[
|
|
"embed", "classify", "score", "token_embed", "token_classify", "plugin"
|
|
]
|
|
POOLING_TASKS: tuple[PoolingTask, ...] = get_args(PoolingTask)
|
|
|
|
# Score API handles score/rerank for:
|
|
# - "score" task (score_type: cross-encoder models)
|
|
# - "embed" task (score_type: bi-encoder models)
|
|
# - "token_embed" task (score_type: late interaction models)
|
|
ScoreType = Literal["bi-encoder", "cross-encoder", "late-interaction"]
|
|
|
|
FrontendTask = Literal["render"]
|
|
FRONTEND_TASKS: tuple[FrontendTask, ...] = get_args(FrontendTask)
|
|
|
|
SupportedTask = Literal[GenerationTask, PoolingTask, FrontendTask]
|