mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
bb766eca0a
* feat: Reduce branch overhead in groupRMSNorm kernels * Fix race condition with sm < 90 and avoid all threads in one warp writing to the same shared memory. Signed-off-by: Simeng Liu <simengl@nvidia.com> --------- Signed-off-by: Simeng Liu <simengl@nvidia.com> |
||
|---|---|---|
| .. | ||
| batch_manager | ||
| common | ||
| cutlass_extensions/include/cutlass_extensions | ||
| executor | ||
| executor_worker | ||
| kernels | ||
| layers | ||
| plugins | ||
| pybind | ||
| runtime | ||
| testing | ||
| thop | ||
| CMakeLists.txt | ||