[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
@@ -7,7 +7,6 @@ from collections.abc import Sequence
import torch
from vllm import envs
from vllm.entrypoints.pooling.typing import AnyPoolingRequest
from vllm.entrypoints.serve.engine.typing import AnyRequest
from vllm.logger import init_logger
from vllm.lora.request import LoRARequest
@@ -70,7 +69,7 @@ class RequestLogger:
lora_request,
)
def log_request_body(self, request: AnyRequest | AnyPoolingRequest) -> None:
def log_request_body(self, request: AnyRequest) -> None:
try:
level = logging.getLevelNamesMapping()[envs.VLLM_REQUEST_BODY_LOG_LEVEL]
except KeyError: