[Mini-VLLM] Cut non-OpenAI surfaces, dead kernels, Mistral stack

- Remove Anthropic, Cohere, SageMaker, decisions, structured-decisions,
  rl, render-launcher and batch entrypoints; keep scale-out token routes
- Drop the Swagger static bundle and the /docs, /redoc routes
- Delete device-keyed tuning configs for fused_moe, quant utils, mamba
  select-state and helion; no sm86 entry ever existed for any of them
- Remove ten unused rope variants plus the fbgemm_fp8 and fp_quant
  quantizers and their config, metrics and loader plumbing
- Cut the CPU device build: csrc/cpu, cpu_extension.cmake, cpu
  requirements and the setup.py cpu target path
- Delete 29 environment variables nothing reads and 14 chat-template
  fallbacks for models this fork no longer registers
- Remove nine dead CUDA ops (deepseek_v4, kimi_k3, minimax, muse_spark,
  dsv3 gemm) with their kernels, bindings, wrappers and CMake entries
- Delete the connector test suites that targeted removed connectors
- Cut the Mistral tokenizer and parser stack, its tests, and the
  mistral_common and ijson dependency pins
- Restore the Qwen4Exp registry rows and nvidia/mtp.py that an earlier
  cut deleted while keeping the model tree

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-10-19 17:10:56 +07:00
co-authored by Hinata
parent bd70a61c20
commit 2066d3143f
1086 changed files with 122 additions and 291919 deletions
@@ -16,7 +16,6 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.scale_out.render.serving import ServingRender
from vllm.exceptions import GenerationError, VLLMValidationError
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.renderers.hf import HfRenderer
@@ -196,58 +195,6 @@ async def test_openai_chat_keeps_mm_cache_for_engine_execution():
)
def _build_serving_render(engine: AsyncLLM) -> ServingRender:
models = OpenAIServingModels(
engine_client=engine,
base_model_paths=BASE_MODEL_PATHS,
)
online_renderer = OnlineRenderer(
model_config=engine.model_config,
renderer=engine.renderer,
request_logger=None,
chat_template=None,
chat_template_content_format="auto",
)
serving_render = ServingRender(models, online_renderer)
async def _fake_preprocess_chat(*args, **kwargs):
# return conversation, engine_inputs
return (
[{"role": "user", "content": "Test"}],
[{"prompt_token_ids": [1, 2, 3]}],
)
serving_render.online_renderer.preprocess_chat = AsyncMock(
side_effect=_fake_preprocess_chat
)
return serving_render
@pytest.mark.asyncio
async def test_renderer_only_chat_request_skips_mm_cache():
mock_engine = MagicMock(spec=AsyncLLM)
mock_engine.errored = False
mock_engine.model_config = MockModelConfig()
mock_engine.input_processor = MagicMock()
mock_engine.renderer = _build_renderer(mock_engine.model_config)
serving_render = _build_serving_render(mock_engine)
request = ChatCompletionRequest(
model=MODEL_NAME,
messages=[{"role": "user", "content": "Test prompt"}],
)
result = await serving_render.render_chat_request(request)
assert result.token_ids == [1, 2, 3]
assert (
serving_render.online_renderer.preprocess_chat.call_args.kwargs["skip_mm_cache"]
is True
)
@pytest.mark.asyncio
@pytest.mark.parametrize("include_usage", [False, True])
async def test_chat_error_stream(include_usage: bool):
@@ -1,101 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import pytest
import requests
from tests.utils import RemoteOpenAIServer
MODEL_NAME = "Qwen/Qwen3-0.6B"
@pytest.fixture(scope="module")
def server():
args = [
"--dtype",
"bfloat16",
"--max-model-len",
"1024",
"--enforce-eager",
"--max-num-seqs",
"32",
"--enable-prefix-caching",
]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
yield remote_server
def test_openai_decisions_text_questions(server):
response = requests.post(
server.url_for("v1/decisions"),
json={
"model": MODEL_NAME,
"input": "The package arrived with a broken screen.",
"questions": [
{"type": "predicate", "instructions": "Is the screen broken?"},
{
"type": "choice",
"name": "department",
"instructions": "Which department should handle this?",
"choices": [{"value": "returns"}, {"value": "billing"}],
},
{
"type": "score",
"name": "damage",
"instructions": "Rate the damage.",
"levels": [{"label": "undamaged"}, {"label": "broken"}],
},
],
},
)
assert response.status_code == 200, response.text
body = response.json()
assert set(body) == {"model", "answers", "usage"}
predicate, choice_answer, score = body["answers"]
assert predicate["type"] == "predicate"
assert predicate["name"] is None
assert 0 <= predicate["probability"] <= 1
assert choice_answer["type"] == "choice"
assert choice_answer["name"] == "department"
assert [p["value"] for p in choice_answer["probabilities"]] == [
"returns",
"billing",
]
assert (
choice_answer["choice"]
== max(choice_answer["probabilities"], key=lambda p: p["probability"])["value"]
)
assert sum(
p["probability"] for p in choice_answer["probabilities"]
) == pytest.approx(1)
assert score["type"] == "score"
assert score["name"] == "damage"
assert [p["label"] for p in score["probabilities"]] == ["undamaged", "broken"]
assert score["score"] == pytest.approx(
sum(p["value"] * p["probability"] for p in score["probabilities"])
)
usage = body["usage"]
assert usage["output_tokens"] == 3
assert usage["total_tokens"] == usage["input_tokens"] + usage["output_tokens"]
def test_openai_decisions_rejects_images(server):
response = requests.post(
server.url_for("v1/decisions"),
json={
"model": MODEL_NAME,
"input": [
{
"role": "user",
"content": [
{
"type": "input_image",
"image_url": "https://example.com/image.png",
}
],
}
],
"questions": [{"type": "predicate", "instructions": "Is this red?"}],
},
)
assert response.status_code == 400
assert "text input only" in response.json()["error"]["message"]
@@ -2,9 +2,7 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Unit tests for the token-offsets request/response protocol wiring:
the request flag flowing into ``TokenizeParams`` and the ``GenerateRequest``
serialization boundary. End-to-end behavior is covered by
``tests/entrypoints/scale_out/render/test_render.py``; plain Pydantic field
storage is not retested here.
serialization boundary. Plain Pydantic field storage is not retested here.
"""
from unittest.mock import Mock