[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
@@ -245,12 +245,6 @@ class ServingGenerativeScoring(BaseServing):
# Note: Mixed item types (string and token list) are validated by
# Pydantic at request parsing time, so we don't need to check here.
try:
lora_request = self._maybe_get_adapters(request) # type: ignore[arg-type]
except (ValueError, TypeError, RuntimeError) as e:
logger.exception("Error preparing request components")
return self.create_error_response(e)
base_id = self._base_request_id(raw_request, default=request.request_id)
request_id = f"generative-scoring-{base_id}"
created_time = int(time.time())
@@ -290,7 +284,6 @@ class ServingGenerativeScoring(BaseServing):
f"{request_id}-{i}",
engine_input,
params=sampling_params,
lora_request=lora_request,
)
try:
@@ -299,7 +292,6 @@ class ServingGenerativeScoring(BaseServing):
engine_inputs,
[sampling_params] * len(engine_inputs),
request_id,
lora_request=lora_request,
trace_headers=trace_headers,
priority=request.priority,
)
@@ -343,7 +335,7 @@ class ServingGenerativeScoring(BaseServing):
total_completion_tokens += len(read.result.outputs[0].token_ids)
# Build response
model_name = self.models.model_name(lora_request)
model_name = self.models.model_name()
response = GenerativeScoringResponse(
id=request_id,
created=created_time,