[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:
@@ -27,15 +27,7 @@ MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def zephyr_lora_files():
|
||||
"""Download zephyr LoRA files once per test session."""
|
||||
from vllm.transformers_utils.repo_utils import hf_api
|
||||
|
||||
return hf_api().snapshot_download(repo_id="typeof/zephyr-7b-beta-lora")
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server(zephyr_lora_files):
|
||||
def server():
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
@@ -43,14 +35,6 @@ def server(zephyr_lora_files):
|
||||
"--max-model-len",
|
||||
"8192",
|
||||
"--enforce-eager",
|
||||
# lora config below
|
||||
"--enable-lora",
|
||||
"--lora-modules",
|
||||
f"zephyr-lora={zephyr_lora_files}",
|
||||
"--max-lora-rank",
|
||||
"64",
|
||||
"--max-cpu-loras",
|
||||
"2",
|
||||
"--max-num-seqs",
|
||||
"128",
|
||||
]
|
||||
@@ -67,9 +51,8 @@ async def client(server):
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
# first test base model, then test loras
|
||||
"model_name",
|
||||
[MODEL_NAME, "zephyr-lora"],
|
||||
[MODEL_NAME],
|
||||
)
|
||||
async def test_no_logprobs_chat(client: openai.AsyncOpenAI, model_name: str):
|
||||
messages = [
|
||||
@@ -91,9 +74,8 @@ async def test_no_logprobs_chat(client: openai.AsyncOpenAI, model_name: str):
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
# just test 1 lora hereafter
|
||||
"model_name",
|
||||
[MODEL_NAME, "zephyr-lora"],
|
||||
[MODEL_NAME],
|
||||
)
|
||||
async def test_zero_logprobs_chat(client: openai.AsyncOpenAI, model_name: str):
|
||||
messages = [
|
||||
@@ -119,7 +101,7 @@ async def test_zero_logprobs_chat(client: openai.AsyncOpenAI, model_name: str):
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
"model_name",
|
||||
[MODEL_NAME, "zephyr-lora"],
|
||||
[MODEL_NAME],
|
||||
)
|
||||
async def test_some_logprobs_chat(client: openai.AsyncOpenAI, model_name: str):
|
||||
messages = [
|
||||
@@ -145,7 +127,7 @@ async def test_some_logprobs_chat(client: openai.AsyncOpenAI, model_name: str):
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
"model_name",
|
||||
[MODEL_NAME, "zephyr-lora"],
|
||||
[MODEL_NAME],
|
||||
)
|
||||
async def test_too_many_chat_logprobs(client: openai.AsyncOpenAI, model_name: str):
|
||||
messages = [
|
||||
@@ -254,7 +236,7 @@ async def test_more_than_one_prompt_logprobs_chat(
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
"model_name",
|
||||
[MODEL_NAME, "zephyr-lora"],
|
||||
[MODEL_NAME],
|
||||
)
|
||||
async def test_single_chat_session(client: openai.AsyncOpenAI, model_name: str):
|
||||
messages = [
|
||||
@@ -297,9 +279,8 @@ async def test_single_chat_session(client: openai.AsyncOpenAI, model_name: str):
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
# just test 1 lora hereafter
|
||||
"model_name",
|
||||
[MODEL_NAME, "zephyr-lora"],
|
||||
[MODEL_NAME],
|
||||
)
|
||||
async def test_chat_streaming(client: openai.AsyncOpenAI, model_name: str):
|
||||
messages = [
|
||||
@@ -345,7 +326,7 @@ async def test_chat_streaming(client: openai.AsyncOpenAI, model_name: str):
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
"model_name",
|
||||
["HuggingFaceH4/zephyr-7b-beta", "zephyr-lora"],
|
||||
["HuggingFaceH4/zephyr-7b-beta"],
|
||||
)
|
||||
async def test_chat_completion_stream_options(
|
||||
client: openai.AsyncOpenAI, model_name: str
|
||||
|
||||
@@ -9,7 +9,6 @@ import openai # use the official client for correctness check
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
|
||||
# downloading lora to test lora requests
|
||||
from tests.utils import ROCM_EXTRA_ARGS, RemoteOpenAIServer
|
||||
|
||||
# any model with a chat template should work here
|
||||
|
||||
Reference in New Issue
Block a user