[Mini-VLLM] Remove LoRA, plugins, speech-to-text and scale-out surfaces

Production runs one static model behind the OpenAI-compatible API. Every
adapter path and non-OpenAI HTTP surface is unreachable there.

- Delete the LoRA stack: vllm/lora, LoRARequest on the engine wire, the
  scheduler, worker, cudagraph and MoE plumbing, LoRA metrics, the lora
  CLI group, and the LoRA tests.
- Drop the plugin loader in vllm/plugins. Platform resolution is now
  CUDA-only and the general/stat-logger plugin hooks are gone.
- Delete the speech-to-text and realtime entrypoints, the scale-out
  render routes, and vllm/config/speech_to_text.py. GenerationTask is
  generate-only.
- Cut DecodeBenchConnector and the disagg-prefill doc and image. The
  Multi, Offloading and Example connectors stay; production uses the
  CPU KV offload tier.
- Delete the ROCm-only fused KDA chunk kernel (2346 lines) with its CMake
  arch gate, declarations and op registrations. The CUDA build never
  defined the guard and no Python caller existed.
- Delete the orphan Mistral and Pixtral chat fixtures and examples/.
- Fix _check_model: removing the LoRA early return made every request
  fail with "The model ... does not exist. Valid aliases: ...".

Verified on an RTX 3090: import sweep reports 1242 modules with 7 known
optional-dependency failures; a live server answers chat, completions,
responses, tokenize and detokenize with zero log errors and 404 for the
removed surfaces; collection yields 8558 tests with the 3 pre-existing
errors; ruff adds no new finding; the incremental _C build succeeds.

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-10-19 21:06:19 +07:00
co-authored by Hinata
parent 5f3c7bd8ab
commit 5aa2ac64f8
269 changed files with 417 additions and 29932 deletions
-8
View File
@@ -13,7 +13,6 @@ from vllm.distributed.weight_transfer.base import (
WeightTransferUpdateRequest,
)
from vllm.inputs import EngineInput, PromptType
from vllm.lora.request import LoRARequest
from vllm.outputs import PoolingRequestOutput, RequestOutput
from vllm.pooling_params import PoolingParams
from vllm.renderers import BaseRenderer
@@ -101,7 +100,6 @@ class EngineClient(ABC):
request_id: str,
*,
prompt_text: str | None = None,
lora_request: LoRARequest | None = None,
tokenization_kwargs: dict[str, Any] | None = None,
trace_headers: Mapping[str, str] | None = None,
priority: int = 0,
@@ -120,7 +118,6 @@ class EngineClient(ABC):
prompt: PromptType | EngineInput,
pooling_params: PoolingParams,
request_id: str,
lora_request: LoRARequest | None = None,
trace_headers: Mapping[str, str] | None = None,
priority: int = 0,
tokenization_kwargs: dict[str, Any] | None = None,
@@ -218,11 +215,6 @@ class EngineClient(ABC):
"""Check whether the engine is sleeping."""
...
@abstractmethod
async def add_lora(self, lora_request: LoRARequest) -> bool:
"""Load a new LoRA adapter into the engine for future requests."""
...
@abstractmethod
async def pause_generation(
self,