biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Hardware][AMD][CI][Bugfix] Fix AMD Quantization test group (#31713)

Browse Source 
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
This commit is contained in:
Matt
2026-01-11 01:19:46 -06:00
committed by GitHub
parent 9103ed1696
commit bde57ab2ed
12 changed files with 114 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
tests/quantization/test_configs.py
View File

@@ -10,6 +10,7 @@ from dataclasses import dataclass
import pytest
from vllm.config import ModelConfig
from vllm.platforms import current_platform
@dataclass
@@ -23,20 +24,44 @@ MODEL_ARG_EXPTYPES = [
# AUTOGPTQ
# compat: autogptq <=0.7.1 is_marlin_format: bool
# Model Serialized in Exllama Format.
("TheBloke/Llama-2-7B-Chat-GPTQ", None, "gptq_marlin"),
("TheBloke/Llama-2-7B-Chat-GPTQ", "marlin", "gptq_marlin"),
(
"TheBloke/Llama-2-7B-Chat-GPTQ",
None,
"gptq_marlin" if current_platform.is_cuda() else "gptq",
),
(
"TheBloke/Llama-2-7B-Chat-GPTQ",
"marlin",
"gptq_marlin" if current_platform.is_cuda() else "ERROR",
),
("TheBloke/Llama-2-7B-Chat-GPTQ", "gptq", "gptq"),
("TheBloke/Llama-2-7B-Chat-GPTQ", "awq", "ERROR"),
# compat: autogptq >=0.8.0 use checkpoint_format: str
# Model Serialized in Exllama Format.
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", None, "gptq_marlin"),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "marlin", "gptq_marlin"),
(
"LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit",
None,
"gptq_marlin" if current_platform.is_cuda() else "gptq",
),
(
"LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit",
"marlin",
"gptq_marlin" if current_platform.is_cuda() else "ERROR",
),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "gptq", "gptq"),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "awq", "ERROR"),
# AUTOAWQ
("TheBloke/OpenHermes-2.5-Mistral-7B-AWQ", None, "awq_marlin"),
(
"TheBloke/OpenHermes-2.5-Mistral-7B-AWQ",
None,
"awq_marlin" if current_platform.is_cuda() else "awq",
),
("TheBloke/OpenHermes-2.5-Mistral-7B-AWQ", "awq", "awq"),
("TheBloke/OpenHermes-2.5-Mistral-7B-AWQ", "marlin", "awq_marlin"),
(
"TheBloke/OpenHermes-2.5-Mistral-7B-AWQ",
"marlin",
"awq_marlin" if current_platform.is_cuda() else "ERROR",
),
("TheBloke/OpenHermes-2.5-Mistral-7B-AWQ", "gptq", "ERROR"),
]