EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Support dynamic LoRA loading / unloading in engine/server API (#7446)

Browse Source
This commit is contained in:
Lifu Huang
2025-06-27 21:00:27 -07:00
committed by GitHub
parent cfe2edac38
commit 49538d111b
14 changed files with 949 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
test/srt/run_suite.py
View File

@@ -17,6 +17,7 @@ suites = {
TestFile("models/lora/test_lora_backend.py", 99),
TestFile("models/lora/test_multi_lora_backend.py", 60),
TestFile("models/lora/test_lora_cuda_graph.py", 250),
TestFile("models/lora/test_lora_update.py", 400),
TestFile("models/test_embedding_models.py", 73),
# TestFile("models/test_clip_models.py", 52),
TestFile("models/test_encoder_embedding_models.py", 100),