[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
@@ -94,7 +94,7 @@ class OpenAIServingCompletion(GenerateBaseServing):
"""Validate the model and preprocess a completion request.
Delegates preprocessing logic to OnlineRenderer, adding the
engine-aware checks (LoRA model validation, engine health).
engine-aware checks (engine health).
Returns:
A list of engine_inputs on success, or an ErrorResponse on failure.
@@ -147,8 +147,6 @@ class OpenAIServingCompletion(GenerateBaseServing):
if raw_request:
raw_request.state.request_metadata = request_metadata
lora_request = self._maybe_get_adapters(request)
# Extract data_parallel_rank from header (router can inject it)
data_parallel_rank = self._get_data_parallel_rank(raw_request)
@@ -182,7 +180,6 @@ class OpenAIServingCompletion(GenerateBaseServing):
request_id_item,
engine_input,
params=sampling_params,
lora_request=lora_request,
)
trace_headers = (
@@ -197,7 +194,6 @@ class OpenAIServingCompletion(GenerateBaseServing):
prompt=engine_input,
request_id=request_id,
params=sampling_params,
lora_request=lora_request,
trace_headers=trace_headers,
session_id=session_id,
)
@@ -206,7 +202,6 @@ class OpenAIServingCompletion(GenerateBaseServing):
engine_input,
sampling_params,
request_id_item,
lora_request=lora_request,
trace_headers=trace_headers,
priority=self._get_priority(request, raw_request),
data_parallel_rank=data_parallel_rank,
@@ -217,7 +212,7 @@ class OpenAIServingCompletion(GenerateBaseServing):
result_generator = merge_async_iterators(*generators)
model_name = self.models.model_name(lora_request)
model_name = self.models.model_name()
num_prompts = len(engine_inputs)
# Streaming response