[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
-28
View File
@@ -55,7 +55,6 @@ from .interfaces import (
supports_multimodal_raw_input_only,
supports_pp,
supports_replayssm,
supports_transcription,
)
from .interfaces_base import (
get_attn_type,
@@ -232,8 +231,6 @@ class _ModelInfo:
is_hybrid: bool
has_noops: bool
supports_replayssm: bool
supports_transcription: bool
supports_transcription_only: bool
supports_kv_cache_grouping: bool
supported_video_pruning_methods: tuple[str, ...]
supports_mm_device_do_normalize: bool
@@ -262,10 +259,6 @@ class _ModelInfo:
is_attention_free=is_attention_free(model),
is_hybrid=is_hybrid(model),
supports_replayssm=supports_replayssm(model),
supports_transcription=supports_transcription(model),
supports_transcription_only=(
supports_transcription(model) and model.supports_transcription_only
),
supports_kv_cache_grouping=supports_kv_cache_grouping(model),
has_noops=has_noops(model),
supported_video_pruning_methods=getattr(
@@ -859,22 +852,6 @@ class _ModelRegistry:
model_info, _ = self.inspect_model_cls(architectures, model_config)
return model_info.has_noops
def is_transcription_model(
self,
architectures: str | list[str],
model_config: ModelConfig,
) -> bool:
model_info, _ = self.inspect_model_cls(architectures, model_config)
return model_info.supports_transcription
def is_transcription_only_model(
self,
architectures: str | list[str],
model_config: ModelConfig,
) -> bool:
model_info, _ = self.inspect_model_cls(architectures, model_config)
return model_info.supports_transcription_only
def _resolve_module_name(mod_relname: str) -> str:
# Allow registry entries to point at fully-qualified module paths (e.g.
@@ -929,11 +906,6 @@ def _run_in_subprocess(fn: Callable[[], _T]) -> _T:
def _run() -> None:
# Setup plugins
from vllm.plugins import load_general_plugins
load_general_plugins()
fn, output_file = pickle.loads(sys.stdin.buffer.read())
result = fn()