xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-14 00:07:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build][AMD] Use float16 in test_reset_prefix_cache_e2e to avoid accuracy issues (#29997)

Browse Source 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
This commit is contained in:
rasmith 2025-12-05 02:42:25 -06:00 committed by GitHub
parent 6038b1b04b
commit feecba09af
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/v1/core/test_reset_prefix_cache_e2e.py
View File

@ -21,6 +21,7 @@ def test_reset_prefix_cache_e2e(monkeypatch):
max_num_batched_tokens=32, max_num_batched_tokens=32,
max_model_len=2048, max_model_len=2048,
compilation_config={"mode": 0}, compilation_config={"mode": 0},
dtype="float16",
) )
engine = LLMEngine.from_engine_args(engine_args) engine = LLMEngine.from_engine_args(engine_args)
sampling_params = SamplingParams( sampling_params = SamplingParams(