xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-08 07:29:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Improve Llama GGUF test robustness (#19287)

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py 2025-06-07 17:23:28 +08:00 committed by GitHub
parent 122cdca5f6
commit d2f0e7e615
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/models/quantization/test_gguf.py
View File

@ -38,7 +38,7 @@ class GGUFTestConfig(NamedTuple):
LLAMA_CONFIG = GGUFTestConfig( LLAMA_CONFIG = GGUFTestConfig(
original_model="meta-llama/Llama-3.2-1B-Instruct", original_model="meta-llama/Llama-3.2-1B-Instruct",
gguf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF", gguf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF",
gguf_filename="Llama-3.2-1B-Instruct-IQ4_XS.gguf", gguf_filename="Llama-3.2-1B-Instruct-Q6_K.gguf",
) )
QWEN2_CONFIG = GGUFTestConfig( QWEN2_CONFIG = GGUFTestConfig(