kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
1ebceb790d
TensorRT-LLMs/cpp/tensorrt_llm/deep_ep
History
Void f172face98
DeepEP LL dispatch FP4 (#6296) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
2025-07-28 11:25:42 +08:00
..
CMakeLists.txt DeepEP LL dispatch FP4 (#6296) 2025-07-28 11:25:42 +08:00
deep_ep_cpp_tllm.version Refactor: move DeepEP from Docker images to wheel building (#5534) 2025-07-07 22:57:03 +09:00
nvshmem_fast_build.patch Refactor: move DeepEP from Docker images to wheel building (#5534) 2025-07-07 22:57:03 +09:00
nvshmem_src_3.2.5-1.txz Refactor: move DeepEP from Docker images to wheel building (#5534) 2025-07-07 22:57:03 +09:00
README.md Refactor: move DeepEP from Docker images to wheel building (#5534) 2025-07-07 22:57:03 +09:00
strip_nvshmem_helper.py Refactor: move DeepEP from Docker images to wheel building (#5534) 2025-07-07 22:57:03 +09:00

README.md

How to generate nvshmem_fast_build.patch?

  1. Build the project without applying the nvshmem_fast_build.patch.
  2. Link NVSHMEM to DeepEP with one NVSHMEM object file omitted.
  3. Repeat step 2 until no more object files can be omitted.
  4. Remove the unused files from NVSHMEM's CMakelists.txt, and save the differences as nvshmem_fast_build.patch.

The script strip_nvshmem_helper.py automatically performs steps 2 and 3.