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

[CI] Prune Quantization Tests and skip compilation (#27038)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-10-16 17:26:35 -04:00
committed by GitHub
parent b3dda72c23
commit 01c977e96d
9 changed files with 62 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/quantization/test_fp8.py
View File

@@ -18,7 +18,6 @@ from vllm.platforms import current_platform
MODELS = [
"neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV",
"nm-testing/Phi-3-mini-128k-instruct-FP8",
"nm-testing/Qwen2-0.5B-Instruct-FP8-SkipQKV",
]
@@ -49,8 +48,6 @@ def test_model_load_and_run(
KV_CACHE_MODELS = [
# Deprecated AutoFP8 format using .kv_scale
"neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV",
# AutoFP8 format using separate .k_scale and .v_scale
"nm-testing/Qwen2-1.5B-Instruct-FP8-K-V",
]