wassname/vllm
1
0 Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-10-01 12:42:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Core] Refactor model loading code (#4097)

Browse Source
This commit is contained in:
Antoni Baum authored and GitHub committed 2024-04-16 11:34:39 -07:00
1 parent 05434764cd
commit 69e1d2fb69
67 files changed
+1054 -963
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/quantization/test_autogptq_marlin_configs.py
-4
View File
@@ -36,8 +36,6 @@ def test_auto_gptq(model_quant_type: str, ) -> None:
model_path,
tokenizer_mode="auto",
trust_remote_code=False,
download_dir=None,
load_format="dummy",
seed=0,
dtype="float16",
revision=None,
@@ -49,8 +47,6 @@ def test_auto_gptq(model_quant_type: str, ) -> None:
model_path,
tokenizer_mode="auto",
trust_remote_code=False,
download_dir=None,
load_format="dummy",
seed=0,
dtype="float16",
revision=None,