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