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>
33 lines
1009 B
Python
33 lines
1009 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
|
|
from typing_extensions import TypedDict
|
|
|
|
|
|
class ServerConfig(TypedDict, total=False):
|
|
model: str
|
|
arguments: list[str]
|
|
system_prompt: str | None
|
|
supports_parallel: bool | None
|
|
supports_rocm: bool | None
|
|
|
|
|
|
ARGS: list[str] = ["--max-model-len", "1024"]
|
|
|
|
CONFIGS: dict[str, ServerConfig] = {
|
|
"mistral": {
|
|
"model": "mistralai/Mistral-7B-Instruct-v0.3",
|
|
"arguments": [
|
|
"--tokenizer-mode",
|
|
"mistral",
|
|
'--ignore-patterns="consolidated.safetensors"',
|
|
],
|
|
"system_prompt": "You are a helpful assistant with access to tools. If a tool"
|
|
" that you have would be helpful to answer a user query, "
|
|
"call the tool. Otherwise, answer the user's query directly "
|
|
"without calling a tool. DO NOT CALL A TOOL THAT IS IRRELEVANT "
|
|
"to the user's question - just respond to it normally.",
|
|
},
|
|
}
|