e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
71 lines
2.9 KiB
Python
71 lines
2.9 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
# Expanded quantized model tests for CPU offloading
|
|
# Base tests: tests/basic_correctness/test_cpu_offload.py
|
|
|
|
import pytest
|
|
|
|
from tests.quantization.utils import is_quant_method_supported
|
|
|
|
from ..utils import compare_two_settings
|
|
|
|
|
|
@pytest.mark.skipif(not is_quant_method_supported("fp8"),
|
|
reason="fp8 is not supported on this GPU type.")
|
|
def test_cpu_offload_fp8():
|
|
# Test quantization of an unquantized checkpoint
|
|
compare_two_settings("meta-llama/Meta-Llama-3-8B-Instruct",
|
|
["--quantization", "fp8"],
|
|
["--quantization", "fp8", "--cpu-offload-gb", "2"],
|
|
max_wait_seconds=480)
|
|
# Test loading a quantized checkpoint
|
|
compare_two_settings("neuralmagic/Meta-Llama-3-8B-Instruct-FP8", [],
|
|
["--cpu-offload-gb", "2"],
|
|
max_wait_seconds=480)
|
|
|
|
|
|
@pytest.mark.skipif(not is_quant_method_supported("gptq_marlin"),
|
|
reason="gptq_marlin is not supported on this GPU type.")
|
|
def test_cpu_offload_gptq():
|
|
# Test GPTQ Marlin
|
|
compare_two_settings("Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4", [],
|
|
["--cpu-offload-gb", "1"],
|
|
max_wait_seconds=480)
|
|
# Test GPTQ
|
|
compare_two_settings("Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4",
|
|
["--quantization", "gptq"],
|
|
["--quantization", "gptq", "--cpu-offload-gb", "1"],
|
|
max_wait_seconds=480)
|
|
|
|
|
|
@pytest.mark.skipif(not is_quant_method_supported("awq_marlin"),
|
|
reason="awq_marlin is not supported on this GPU type.")
|
|
def test_cpu_offload_awq():
|
|
# Test AWQ Marlin
|
|
compare_two_settings("Qwen/Qwen2-1.5B-Instruct-AWQ", [],
|
|
["--cpu-offload-gb", "1"],
|
|
max_wait_seconds=480)
|
|
# Test AWQ
|
|
compare_two_settings("Qwen/Qwen2-1.5B-Instruct-AWQ",
|
|
["--quantization", "awq"],
|
|
["--quantization", "awq", "--cpu-offload-gb", "1"],
|
|
max_wait_seconds=480)
|
|
|
|
|
|
@pytest.mark.skipif(not is_quant_method_supported("gptq_marlin"),
|
|
reason="gptq_marlin is not supported on this GPU type.")
|
|
def test_cpu_offload_compressed_tensors():
|
|
# Test wNa16
|
|
compare_two_settings("nm-testing/tinyllama-oneshot-w4a16-channel-v2", [],
|
|
["--cpu-offload-gb", "1"],
|
|
max_wait_seconds=480)
|
|
# Test w4a16_marlin24
|
|
compare_two_settings("nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t",
|
|
[], ["--cpu-offload-gb", "1"],
|
|
max_wait_seconds=480)
|
|
# Test w8a8
|
|
compare_two_settings(
|
|
"nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", [],
|
|
["--cpu-offload-gb", "1"],
|
|
max_wait_seconds=480)
|