[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:
@@ -265,7 +265,7 @@ class OpenAIServingChat(GenerateBaseServing):
|
||||
"""Validate the model and preprocess a chat completion request.
|
||||
|
||||
Delegates preprocessing logic to OnlineRenderer, adding the
|
||||
engine-aware checks (LoRA model validation, engine health).
|
||||
engine-aware checks (engine health).
|
||||
|
||||
Returns:
|
||||
A tuple of (conversation, engine_inputs) on success,
|
||||
@@ -322,9 +322,7 @@ class OpenAIServingChat(GenerateBaseServing):
|
||||
if raw_request:
|
||||
raw_request.state.request_metadata = request_metadata
|
||||
|
||||
lora_request = self._maybe_get_adapters(request, supports_default_mm_loras=True)
|
||||
|
||||
model_name = self.models.model_name(lora_request)
|
||||
model_name = self.models.model_name()
|
||||
|
||||
# Extract data_parallel_rank from header (router can inject it)
|
||||
data_parallel_rank = self._get_data_parallel_rank(raw_request)
|
||||
@@ -369,7 +367,6 @@ class OpenAIServingChat(GenerateBaseServing):
|
||||
sub_request_id,
|
||||
engine_input,
|
||||
params=sampling_params,
|
||||
lora_request=lora_request,
|
||||
)
|
||||
|
||||
trace_headers = (
|
||||
@@ -384,7 +381,6 @@ class OpenAIServingChat(GenerateBaseServing):
|
||||
prompt=engine_input,
|
||||
request_id=sub_request_id,
|
||||
params=sampling_params,
|
||||
lora_request=lora_request,
|
||||
trace_headers=trace_headers,
|
||||
session_id=session_id,
|
||||
)
|
||||
@@ -393,7 +389,6 @@ class OpenAIServingChat(GenerateBaseServing):
|
||||
engine_input,
|
||||
sampling_params,
|
||||
sub_request_id,
|
||||
lora_request=lora_request,
|
||||
trace_headers=trace_headers,
|
||||
priority=self._get_priority(request, raw_request),
|
||||
data_parallel_rank=data_parallel_rank,
|
||||
|
||||
Reference in New Issue
Block a user