[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:
@@ -9,12 +9,10 @@ from tests.utils import RemoteOpenAIServer
|
||||
|
||||
# any model with a chat template should work here
|
||||
MODEL_NAME = "Qwen/Qwen3-0.6B"
|
||||
# technically this needs Mistral-7B-v0.1 as base, but we're not testing
|
||||
# generation quality here
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server(qwen3_lora_files):
|
||||
def server():
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
@@ -22,14 +20,6 @@ def server(qwen3_lora_files):
|
||||
"--max-model-len",
|
||||
"8192",
|
||||
"--enforce-eager",
|
||||
# lora config below
|
||||
"--enable-lora",
|
||||
"--lora-modules",
|
||||
f"qwen3-lora={qwen3_lora_files}",
|
||||
"--max-lora-rank",
|
||||
"64",
|
||||
"--max-cpu-loras",
|
||||
"2",
|
||||
"--max-num-seqs",
|
||||
"128",
|
||||
]
|
||||
@@ -45,12 +35,9 @@ async def client(server):
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_check_models(client: openai.AsyncOpenAI, qwen3_lora_files):
|
||||
async def test_check_models(client: openai.AsyncOpenAI):
|
||||
models = await client.models.list()
|
||||
models = models.data
|
||||
served_model = models[0]
|
||||
lora_models = models[1:]
|
||||
assert served_model.id == MODEL_NAME
|
||||
assert served_model.root == MODEL_NAME
|
||||
assert all(lora_model.root == qwen3_lora_files for lora_model in lora_models)
|
||||
assert lora_models[0].id == "qwen3-lora"
|
||||
|
||||
Reference in New Issue
Block a user