[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
-19
View File
@@ -1534,29 +1534,10 @@ def num_gpus_available():
temp_dir = tempfile.gettempdir()
_dummy_opt_path = os.path.join(temp_dir, "dummy_opt")
_dummy_llava_path = os.path.join(temp_dir, "dummy_llava")
_dummy_gemma2_embedding_path = os.path.join(temp_dir, "dummy_gemma2_embedding")
@pytest.fixture
def dummy_opt_path():
json_path = os.path.join(_dummy_opt_path, "config.json")
if not os.path.exists(_dummy_opt_path):
hf_api().snapshot_download(
repo_id="facebook/opt-125m",
local_dir=_dummy_opt_path,
ignore_patterns=["*.bin", "*.bin.index.json", "*.pt", "*.h5", "*.msgpack"],
)
assert os.path.exists(json_path)
with open(json_path) as f:
config = json.load(f)
config["architectures"] = ["MyOPTForCausalLM"]
with open(json_path, "w") as f:
json.dump(config, f)
return _dummy_opt_path
@pytest.fixture
def dummy_llava_path():
json_path = os.path.join(_dummy_llava_path, "config.json")