Add smoke test for non-uniform AutoFP8 quantization

vllm-project · Jul 23, 2024 · d2079c8 · d2079c8
1 parent 58f5303
commit d2079c8
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/tests/quantization/test_fp8.py b/tests/quantization/test_fp8.py
@@ -13,6 +13,7 @@
 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",
 ]