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

6
tests/quantization/test_gptq_dynamic.py
View File

@@ -14,6 +14,7 @@ from vllm.model_executor.layers.quantization.gptq_marlin import GPTQMarlinLinear
from vllm.model_executor.layers.quantization.utils.gptq_utils import (
get_dynamic_override,
)
from vllm.platforms import current_platform
PROMPT = "On the surface of Mars, we found"
@@ -21,7 +22,10 @@ PROMPT = "On the surface of Mars, we found"
# The second layer is quantized using bits=8, group_size=32
# All other layers (layer index >= 2) are not quantized
MODEL_QUANT = [
("ModelCloud/Qwen1.5-1.8B-Chat-GPTQ-4bits-dynamic-cfg-with-lm_head-symTrue", True),
(
"ModelCloud/Qwen1.5-1.8B-Chat-GPTQ-4bits-dynamic-cfg-with-lm_head-symTrue",
current_platform.is_cuda(),
),
(
"ModelCloud/Qwen1.5-1.8B-Chat-GPTQ-4bits-dynamic-cfg-with-lm_head-symFalse",
False,