[Feature] Initial support for multi-LoRA serving (#1307)

2024-09-12 16:46:14 -07:00
parent c33d82a211
commit 712216928f
21 changed files with 1435 additions and 22 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -7,6 +7,7 @@ suites = {
    "minimal": [
        "models/test_embedding_models.py",
        "models/test_generation_models.py",
+        "models/test_lora.py",
        "sampling/penaltylib",
        "test_chunked_prefill.py",
        "test_embedding_openai_server.py",