[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:
2026-10-19 17:10:56 +07:00
co-authored by Hinata
parent bd70a61c20
commit 2066d3143f
1086 changed files with 122 additions and 291919 deletions
-38
View File
@@ -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))