[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:
@@ -16,7 +16,6 @@ from vllm.inputs import (
|
||||
split_enc_dec_input,
|
||||
)
|
||||
from vllm.logger import init_logger
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
|
||||
from vllm.multimodal.encoder_budget import MultiModalBudget
|
||||
from vllm.multimodal.inputs import MultiModalFeatureSpec
|
||||
@@ -49,7 +48,6 @@ class InputProcessor:
|
||||
self.vllm_config = vllm_config
|
||||
self.model_config = model_config = vllm_config.model_config
|
||||
self.cache_config = vllm_config.cache_config
|
||||
self.lora_config = vllm_config.lora_config
|
||||
self.scheduler_config = vllm_config.scheduler_config
|
||||
self.speculative_config = vllm_config.speculative_config
|
||||
self.structured_outputs_config = vllm_config.structured_outputs_config
|
||||
@@ -275,42 +273,6 @@ class InputProcessor:
|
||||
sampling_params.stop_token_ids = []
|
||||
sampling_params._all_stop_token_ids = set()
|
||||
|
||||
def _validate_lora(self, lora_request: LoRARequest | None) -> None:
|
||||
if lora_request is None:
|
||||
return
|
||||
|
||||
# LoRA request passed in while LoRA is not enabled
|
||||
if not self.lora_config:
|
||||
raise VLLMValidationError(
|
||||
f"Got lora_request {lora_request} but LoRA is not enabled!"
|
||||
)
|
||||
|
||||
if self.tokenizer is not None:
|
||||
logger.warning_once(
|
||||
"vLLM has deprecated support for supporting different "
|
||||
"tokenizers for different LoRAs. By default, vLLM uses base "
|
||||
"model's tokenizer. If you are using a LoRA "
|
||||
"with its own tokenizer, consider specifying `--tokenizer "
|
||||
"[lora_path]` to use the LoRA tokenizer."
|
||||
)
|
||||
|
||||
def _get_mm_identifier(
|
||||
self,
|
||||
mm_hash: str,
|
||||
lora_request: LoRARequest | None,
|
||||
) -> str:
|
||||
"""When enable_tower_connector_lora is True, multi-modal embeddings
|
||||
vary depending on the LoRA request. Therefore, the mm_hash must be
|
||||
generated based on the LoRA request to prevent incorrect cache hits.
|
||||
"""
|
||||
if (
|
||||
lora_request is None
|
||||
or self.lora_config is None
|
||||
or not self.lora_config.enable_tower_connector_lora
|
||||
):
|
||||
return mm_hash
|
||||
return f"{lora_request.lora_name}:{mm_hash}"
|
||||
|
||||
def inject_into_mm_cache(
|
||||
self,
|
||||
mm_hashes: dict[str, list[str]],
|
||||
@@ -377,7 +339,6 @@ class InputProcessor:
|
||||
params: SamplingParams | PoolingParams,
|
||||
supported_tasks: tuple[SupportedTask, ...],
|
||||
arrival_time: float | None = None,
|
||||
lora_request: LoRARequest | None = None,
|
||||
tokenization_kwargs: dict[str, Any] | None = None,
|
||||
trace_headers: Mapping[str, str] | None = None,
|
||||
priority: int = 0,
|
||||
@@ -387,7 +348,6 @@ class InputProcessor:
|
||||
kv_hints: KvHintsEnvelope | None = None,
|
||||
) -> EngineCoreRequest:
|
||||
watermarking = self._validate_params(params, supported_tasks)
|
||||
self._validate_lora(lora_request)
|
||||
|
||||
parallel_config = self.vllm_config.parallel_config
|
||||
dp_size = parallel_config.data_parallel_size
|
||||
@@ -526,10 +486,7 @@ class InputProcessor:
|
||||
MultiModalFeatureSpec(
|
||||
data=decoder_mm_inputs[modality][idx],
|
||||
modality=modality,
|
||||
identifier=self._get_mm_identifier(
|
||||
base_mm_hash,
|
||||
lora_request,
|
||||
),
|
||||
identifier=base_mm_hash,
|
||||
mm_position=decoder_mm_positions[modality][idx],
|
||||
mm_hash=base_mm_hash,
|
||||
)
|
||||
@@ -544,7 +501,6 @@ class InputProcessor:
|
||||
sampling_params=sampling_params,
|
||||
pooling_params=pooling_params,
|
||||
arrival_time=arrival_time,
|
||||
lora_request=lora_request,
|
||||
cache_salt=decoder_input.get("cache_salt"),
|
||||
priority=priority,
|
||||
data_parallel_rank=data_parallel_rank,
|
||||
|
||||
Reference in New Issue
Block a user