[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:
@@ -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,
|
||||
|
||||
Reference in New Issue
Block a user