Revert "[feat] Enable chunked prefill for llava-onevision" (#2329)

This commit is contained in:
Ying Sheng
2024-12-02 23:11:13 -08:00
committed by GitHub
parent 3ddb1c4679
commit aa47f64223
5 changed files with 18 additions and 221 deletions

View File

@@ -39,7 +39,6 @@ suites = {
"test_triton_attention_kernels.py",
"test_triton_attention_backend.py",
"test_update_weights_from_disk.py",
"test_vision_chunked_prefill.py",
"test_vision_openai_server.py",
"test_session_control.py",
],