Files
FastDeploy/fastdeploy/worker/gpu_model_runner.py
freeliuzc 6eada4929d [Speculative Decoding]Support multi-step mtp with cudagraph (#5624)
* support multi-step mtp with cudagraph

* fix usage

* fix unit test
2025-12-22 11:34:04 +08:00

148 KiB