A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 07:15 UTC
[CI/Build] Improve Llama GGUF test robustness (#19287)
Signed-off-by: Isotr0py <2037008807@qq.com>
Isotr0py committed
Jun 7, 2025 at 17:23 UTC
d2f0e7e6158bf0c0995ebe09c4d95ee1b24c5607
1 file changed
+1
-1
tests/models/quantization/test_gguf.py
+1
-1
@@ -38,7 +38,7 @@ class GGUFTestConfig(NamedTuple):
38
LLAMA_CONFIG = GGUFTestConfig(
39
original_model="meta-llama/Llama-3.2-1B-Instruct",
40
gguf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF",
41
- gguf_filename="Llama-3.2-1B-Instruct-IQ4_XS.gguf",
41
+ gguf_filename="Llama-3.2-1B-Instruct-Q6_K.gguf",
42
)
43
44
QWEN2_CONFIG = GGUFTestConfig(