Feat: support cuda graph for LoRA (#4115)

Co-authored-by: Beichen Ma <mabeichen12@gmail.com>
2025-04-29 02:30:44 -04:00
parent 2c3ea29476
commit 8c0cfca87d
13 changed files with 366 additions and 55 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -1242,7 +1242,6 @@ class ServerArgs:
        assert (
            self.max_loras_per_batch > 0
            # FIXME
-            and (self.lora_paths is None or self.disable_cuda_graph)
            and (self.lora_paths is None or self.disable_radix_cache)
        ), "compatibility of lora and cuda graph and radix attention is in progress"
        assert self.base_gpu_id >= 0, "base_gpu_id must be non-negative"