Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
33 lines
974 B
Python
33 lines
974 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Test model set-up and inference for quantized HF models supported
|
|
on the GPU backend using FPQuant.
|
|
|
|
Validating the configuration and printing results for manual checking.
|
|
|
|
Run `pytest tests/quantization/test_fp_quant.py`.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from tests.quantization.utils import is_quant_method_supported
|
|
|
|
MODELS = [
|
|
"ISTA-DASLab/Qwen3-0.6B-RTN-NVFP4",
|
|
"ISTA-DASLab/Qwen3-0.6B-RTN-MXFP4",
|
|
]
|
|
DTYPE = ["bfloat16"]
|
|
EAGER = [True, False]
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not is_quant_method_supported("fp_quant"),
|
|
reason="FPQuant is not supported on this GPU type.",
|
|
)
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("eager", EAGER)
|
|
def test_fpquant(vllm_runner, model, eager):
|
|
with vllm_runner(model, enforce_eager=eager) as llm:
|
|
output = llm.generate_greedy(["1 2 3 4 5"], max_tokens=2)
|
|
assert output[0][1] == "1 2 3 4 5 6"
|