[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
+1 -6
View File
@@ -30,7 +30,6 @@ from vllm.config.quantization import QuantizationConfigArgs
from vllm.engine.arg_utils import EngineArgs
from vllm.entrypoints.common.offline import _O, _R, OfflineInferenceMixin
from vllm.entrypoints.generate.beam_search.offline import BeamSearchOfflineMixin
from vllm.entrypoints.pooling.offline import PoolingOfflineMixin
from vllm.entrypoints.rl.offline import RLOfflineMixin
from vllm.entrypoints.serve.utils.api_utils import log_non_default_args
from vllm.inputs import PromptType
@@ -60,9 +59,7 @@ if TYPE_CHECKING:
logger = init_logger(__name__)
class LLM(
BeamSearchOfflineMixin, PoolingOfflineMixin, RLOfflineMixin, OfflineInferenceMixin
):
class LLM(BeamSearchOfflineMixin, RLOfflineMixin, OfflineInferenceMixin):
"""An LLM for generating texts from given prompts and sampling parameters.
This class includes a tokenizer, a language model (possibly distributed
@@ -373,8 +370,6 @@ class LLM(
self.model_config.renderer_num_workers,
)
PoolingOfflineMixin.__init__(self)
# Cache for __repr__ to avoid repeated collective_rpc calls
self._cached_repr: str | None = None