[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
-22
View File
@@ -20,7 +20,6 @@ from starlette.background import BackgroundTask, BackgroundTasks
from vllm import envs
from vllm.engine.arg_utils import EngineArgs
from vllm.entrypoints.generate.base.protocol import StreamOptions
from vllm.entrypoints.openai.models.protocol import LoRAModulePath
from vllm.logger import current_formatter_type, init_logger
from vllm.platforms import current_platform
from vllm.utils.argparse_utils import FlexibleArgumentParser
@@ -372,27 +371,6 @@ def should_include_usage(
return include_usage, include_continuous_usage
def process_lora_modules(
args_lora_modules: list[LoRAModulePath], default_mm_loras: dict[str, str] | None
) -> list[LoRAModulePath]:
from vllm.entrypoints.openai.models.serving import LoRAModulePath
lora_modules = args_lora_modules
if default_mm_loras:
default_mm_lora_paths = [
LoRAModulePath(
name=modality,
path=lora_path,
)
for modality, lora_path in default_mm_loras.items()
]
if args_lora_modules is None:
lora_modules = default_mm_lora_paths
else:
lora_modules += default_mm_lora_paths
return lora_modules
def log_version_and_model(lgr: Logger, version: str, model_name: str) -> None:
if envs.VLLM_DISABLE_LOG_LOGO or (formatter := current_formatter_type(lgr)) is None:
message = "vLLM server version %s, serving model %s"