[Mini-vLLM] SM86-only cut: models, backends, Rust, tests

- Keep only Qwen3.5, Qwen3.5-MTP and Qwen4Exp model paths; trim the model registry to 41 entries
- Delete idle attention backends (MLA, FlashInfer, ROCm-only, quant backends) and dead GDN CuTeDSL kernels
- Remove inc/quark quant loaders; keep compressed-tensors and Marlin
- Drop the Rust frontend, pooling entrypoints, and idle test suites
- Rebuild kernels for sm_80;sm_86 and strip the extensions
- Verified: full import sweep clean (optional deps only) and a dummy-load Qwen3.5 engine run on RTX 3090 via the Triton GDN path

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-10-18 19:19:56 +07:00
co-authored by Hinata
parent c5ab42bc0f
commit e61dcb9143
2728 changed files with 159 additions and 950401 deletions
@@ -18,7 +18,7 @@ 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, POOLING_TASKS, SupportedTask
from vllm.tasks import FALLBACK_SUPPORTED_TASKS, SupportedTask
async def init_app_state(
@@ -152,11 +152,6 @@ async def init_app_state(
engine_client, state, args, request_logger, supported_tasks
)
if any(task in POOLING_TASKS for task in supported_tasks):
from vllm.entrypoints.pooling.factories import init_pooling_state
init_pooling_state(engine_client, state, args, request_logger, supported_tasks)
from vllm.entrypoints.generate.structured_decisions.api_router import (
init_structured_decisions_state,
)
@@ -6,7 +6,7 @@ from fastapi import FastAPI
from vllm import envs
from vllm.config import ModelConfig
from vllm.tasks import POOLING_TASKS, SupportedTask
from vllm.tasks import SupportedTask
def register_api_routers(
@@ -77,11 +77,6 @@ def register_api_routers(
register_speech_to_text_api_routers(app, supported_tasks)
if any(task in POOLING_TASKS for task in supported_tasks):
from vllm.entrypoints.pooling.factories import register_pooling_api_routers
register_pooling_api_routers(app, supported_tasks, model_config)
if getattr(args, "enable_fault_tolerance", False):
from vllm.entrypoints.serve.fault_tolerance.api_router import (
register_fault_tolerance_api_router,