[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
+1 -26
View File
@@ -21,7 +21,6 @@ from transformers.video_processing_utils import BaseVideoProcessor
from typing_extensions import TypeVar
from vllm.logger import init_logger
from vllm.transformers_utils import processors
from vllm.transformers_utils.repo_utils import (
get_hf_file_to_dict,
get_non_weight_snapshot_path,
@@ -151,18 +150,6 @@ def get_processor_config(
return {}
def get_processor_cls_name_from_config(
processor_name: str,
revision: str | None = "main",
) -> str | None:
config = get_processor_config(processor_name, revision=revision)
if not config:
return None
return config["processor_class"]
def get_video_processor_cls_name_from_config(
processor_name: str,
revision: str | None = "main",
@@ -223,20 +210,8 @@ def get_processor(
processor_name = get_non_weight_snapshot_path(
processor_name, revision=revision, token=kwargs.get("token")
)
registered_cls_name = get_processor_cls_name_from_config(
processor_name, revision=revision
)
registered_processor_cls = (
getattr(processors, registered_cls_name, None)
if registered_cls_name
else None
)
registered_processor_cls = cast(type[_P] | None, registered_processor_cls)
# Use registered processor class when it's available
# and explicit processor_cls is not set.
if isinstance(processor_cls, tuple) or processor_cls == ProcessorMixin:
_processor_cls = registered_processor_cls or AutoProcessor
processor = _processor_cls.from_pretrained(
processor = AutoProcessor.from_pretrained(
processor_name,
*args,
revision=revision,