[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:
@@ -7,7 +7,6 @@ from typing import cast
|
||||
from starlette.datastructures import State
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.launchers.cli_args import resolve_default_chat_template_kwargs
|
||||
from vllm.entrypoints.mcp.tool_server import init_tool_server
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
@@ -16,7 +15,6 @@ from vllm.entrypoints.serve.utils.api_utils import process_lora_modules
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.plugins.endpoint_plugins.interface import init_endpoint_plugins_state
|
||||
from vllm.renderers.chat_utils import load_chat_template
|
||||
from vllm.renderers.online_derenderer import OnlineDerenderer
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
from vllm.tasks import FALLBACK_SUPPORTED_TASKS, SupportedTask
|
||||
|
||||
@@ -65,7 +63,7 @@ async def init_app_state(
|
||||
state.vllm_config = vllm_config
|
||||
state.args = args
|
||||
resolved_chat_template = load_chat_template(args.chat_template)
|
||||
default_chat_template_kwargs = resolve_default_chat_template_kwargs(args)
|
||||
default_chat_template_kwargs = dict(args.default_chat_template_kwargs or {})
|
||||
state.tool_server = (
|
||||
await init_tool_server(args) if "generate" in supported_tasks else None
|
||||
)
|
||||
@@ -103,22 +101,6 @@ async def init_app_state(
|
||||
)
|
||||
state.online_renderer.warmup()
|
||||
|
||||
state.online_derenderer = OnlineDerenderer(
|
||||
model_config=engine_client.model_config,
|
||||
renderer=engine_client.renderer,
|
||||
request_logger=request_logger,
|
||||
chat_template=resolved_chat_template,
|
||||
chat_template_content_format=args.chat_template_content_format,
|
||||
trust_request_chat_template=args.trust_request_chat_template,
|
||||
enable_auto_tools=args.enable_auto_tool_choice,
|
||||
exclude_tools_when_tool_choice_none=args.exclude_tools_when_tool_choice_none,
|
||||
tool_parser=args.tool_call_parser,
|
||||
tool_strict_level=args.tool_strict_level,
|
||||
reasoning_parser=args.structured_outputs_config.reasoning_parser,
|
||||
default_chat_template_kwargs=default_chat_template_kwargs,
|
||||
log_error_stack=args.log_error_stack,
|
||||
)
|
||||
|
||||
state.serving_tokenization = ServingTokenization(
|
||||
state.openai_serving_models,
|
||||
state.online_renderer,
|
||||
@@ -152,19 +134,6 @@ async def init_app_state(
|
||||
engine_client, state, args, request_logger, supported_tasks
|
||||
)
|
||||
|
||||
from vllm.entrypoints.generate.structured_decisions.api_router import (
|
||||
init_structured_decisions_state,
|
||||
)
|
||||
|
||||
init_structured_decisions_state(
|
||||
engine_client,
|
||||
state,
|
||||
args,
|
||||
request_logger,
|
||||
supported_tasks,
|
||||
default_chat_template_kwargs,
|
||||
)
|
||||
|
||||
await init_endpoint_plugins_state(engine_client, state, args)
|
||||
|
||||
state.enable_server_load_tracking = args.enable_server_load_tracking
|
||||
|
||||
@@ -25,33 +25,11 @@ def register_api_routers(
|
||||
|
||||
register_models_api_router(app)
|
||||
|
||||
from vllm.entrypoints.generate.structured_decisions.api_router import (
|
||||
register_structured_decisions_api_router,
|
||||
)
|
||||
|
||||
register_structured_decisions_api_router(app)
|
||||
|
||||
from vllm.entrypoints.openai.decisions.api_router import (
|
||||
register_decisions_api_router,
|
||||
)
|
||||
|
||||
register_decisions_api_router(app)
|
||||
|
||||
from vllm.entrypoints.serve.sagemaker.api_router import (
|
||||
attach_router as register_sagemaker_api_router,
|
||||
)
|
||||
|
||||
register_sagemaker_api_router(app, supported_tasks, model_config)
|
||||
|
||||
if envs.VLLM_SERVER_DEV_MODE:
|
||||
from vllm.entrypoints.serve import register_vllm_dev_api_routers
|
||||
|
||||
register_vllm_dev_api_routers(app)
|
||||
|
||||
from vllm.entrypoints.rl.factories import register_rl_api_routers
|
||||
|
||||
register_rl_api_routers(app)
|
||||
|
||||
if "generate" in supported_tasks:
|
||||
from vllm.entrypoints.generate.api_router import (
|
||||
register_generate_api_routers,
|
||||
@@ -59,13 +37,6 @@ def register_api_routers(
|
||||
|
||||
register_generate_api_routers(app)
|
||||
|
||||
from vllm.entrypoints.serve.elastic_ep.api_router import (
|
||||
attach_router as elastic_ep_attach_router,
|
||||
)
|
||||
|
||||
elastic_ep_attach_router(app)
|
||||
|
||||
if "generate" in supported_tasks or "render" in supported_tasks:
|
||||
from vllm.entrypoints.scale_out.factories import register_scale_out_api_routers
|
||||
|
||||
register_scale_out_api_routers(app, supported_tasks)
|
||||
|
||||
Reference in New Issue
Block a user