[8/n] decouple quantization impl from vllm dependency - gguf srt (#11964)
Co-authored-by: Peng Zhang <zhuangsen.zp@antgroup.com>
This commit is contained in:
@@ -197,7 +197,7 @@ suites = {
|
||||
TestFile("test_bnb.py", 5),
|
||||
TestFile("test_gptqmodel_dynamic.py", 102),
|
||||
TestFile("test_vllm_dependency.py", 185),
|
||||
# TestFile("test_gguf.py", 96),
|
||||
TestFile("test_gguf.py", 96),
|
||||
],
|
||||
# If the test cases take too long, considering adding them to nightly tests instead of per-commit tests
|
||||
"nightly-1-gpu": [],
|
||||
|
||||
Reference in New Issue
Block a user