[Mini-VLLM] Cut non-OpenAI surfaces, dead kernels, Mistral stack
- Remove Anthropic, Cohere, SageMaker, decisions, structured-decisions, rl, render-launcher and batch entrypoints; keep scale-out token routes - Drop the Swagger static bundle and the /docs, /redoc routes - Delete device-keyed tuning configs for fused_moe, quant utils, mamba select-state and helion; no sm86 entry ever existed for any of them - Remove ten unused rope variants plus the fbgemm_fp8 and fp_quant quantizers and their config, metrics and loader plumbing - Cut the CPU device build: csrc/cpu, cpu_extension.cmake, cpu requirements and the setup.py cpu target path - Delete 29 environment variables nothing reads and 14 chat-template fallbacks for models this fork no longer registers - Remove nine dead CUDA ops (deepseek_v4, kimi_k3, minimax, muse_spark, dsv3 gemm) with their kernels, bindings, wrappers and CMake entries - Delete the connector test suites that targeted removed connectors - Cut the Mistral tokenizer and parser stack, its tests, and the mistral_common and ijson dependency pins - Restore the Qwen4Exp registry rows and nvidia/mtp.py that an earlier cut deleted while keeping the model tree Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
@@ -1,38 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""Provides lazy import of the vllm.tokenizers.mistral module."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, TypeGuard
|
||||
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.utils.import_utils import LazyLoader
|
||||
|
||||
if TYPE_CHECKING:
|
||||
# if type checking, eagerly import the module
|
||||
import vllm.tokenizers.mistral as mt
|
||||
else:
|
||||
mt = LazyLoader("mt", globals(), "vllm.tokenizers.mistral")
|
||||
|
||||
|
||||
def is_mistral_tokenizer(obj: TokenizerLike | None) -> TypeGuard[mt.MistralTokenizer]:
|
||||
"""Return true if the tokenizer is a MistralTokenizer instance."""
|
||||
cls = type(obj)
|
||||
# Check for special class attribute, this avoids importing the class to
|
||||
# do an isinstance() check. If the attribute is True, do an isinstance
|
||||
# check to be sure we have the correct type.
|
||||
return bool(
|
||||
getattr(cls, "IS_MISTRAL_TOKENIZER", False)
|
||||
and isinstance(obj, mt.MistralTokenizer)
|
||||
)
|
||||
|
||||
|
||||
def is_mistral_tool_parser(cls: type | None) -> bool:
|
||||
"""Return true if *cls* carries the ``IS_MISTRAL_TOOL_PARSER`` marker.
|
||||
|
||||
The marker is set on the engine-adapter subclass registered under the
|
||||
``"mistral"`` tool-parser key. No import of the parser module is
|
||||
required.
|
||||
"""
|
||||
return bool(getattr(cls, "IS_MISTRAL_TOOL_PARSER", False))
|
||||
Reference in New Issue
Block a user