A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Misc] Fix comments in `tests/kernels/quantization` (#23675)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Jiangyun Zhu committed
Aug 27, 2025 at 03:31 UTC
c37c0af990ed1f3623448b82903c1ae52e84cc05
7 files changed
+7
-7
tests/kernels/quantization/test_awq_triton.py
+1
-1
@@ -2,7 +2,7 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
"""Tests for the AWQ Triton kernel.
4
5
-Run `pytest tests/kernels/test_awq_triton.py`.
5
+Run `pytest tests/kernels/quantization/test_awq_triton.py`.
6
"""
7
import pytest
8
import torch
tests/kernels/quantization/test_cutlass_2of4_sparse.py
+1
-1
@@ -2,7 +2,7 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
"""Tests for sparse cutlass kernels
4
5
-Run `pytest tests/kernels/test_semi_structured.py`.
5
+Run `pytest tests/kernels/quantization/test_cutlass_2of4_sparse.py`.
6
"""
7
8
import pytest
tests/kernels/quantization/test_cutlass_scaled_mm.py
+1
-1
@@ -2,7 +2,7 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
"""Tests for cutlass kernels
4
5
-Run `pytest tests/kernels/test_cutlass.py`.
5
+Run `pytest tests/kernels/quantization/test_cutlass_scaled_mm.py`.
6
"""
7
import random
8
tests/kernels/quantization/test_cutlass_w4a8.py
+1
-1
@@ -2,7 +2,7 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
"""Tests for the CUTLASS W4A8 kernel.
4
5
-Run `pytest tests/kernels/test_cutlass_w4a8.py`.
5
+Run `pytest tests/kernels/quantization/test_cutlass_w4a8.py`.
6
"""
7
8
from dataclasses import dataclass
tests/kernels/quantization/test_machete_mm.py
+1
-1
@@ -2,7 +2,7 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
"""Tests for the machete kernel.
4
5
-Run `pytest tests/kernels/test_machete_mm.py`.
5
+Run `pytest tests/kernels/quantization/test_machete_mm.py`.
6
"""
7
8
import math
tests/kernels/quantization/test_marlin_gemm.py
+1
-1
@@ -2,7 +2,7 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
"""Tests for the marlin kernel.
4
5
-Run `pytest tests/kernels/marlin/test_marlin_gemm.py`.
5
+Run `pytest tests/kernels/quantization/test_marlin_gemm.py`.
6
"""
7
import pytest
8
import torch
tests/kernels/quantization/test_triton_scaled_mm.py
+1
-1
@@ -2,7 +2,7 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
"""Tests for the triton_scaled_mm kernel
4
5
-Run `pytest tests/kernels/test_triton_scaled_mm.py`.
5
+Run `pytest tests/kernels/quantization/test_triton_scaled_mm.py`.
6
"""
7
import importlib
8
from typing import Optional