DeepSeek/DeepEP
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepEP synced 2025-06-26 18:28:11 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Support Ampere architecture (#204)

Browse Source 
* Update README

* Update `setup.py`

* Fix headers

* Add `DISABLE_NVSHMEM` for APIs

* Fix launch

* Fix TMA settings

* Fix TMA usages

* Fix dlink

* Separate layout kernels

* Update version

* Add `is_sm90_compiled`

* Fix tests

* Add NVLink connection checks

* Update README

* Fix tests

* Add some comments

* Minor fix

* Minor fix

* Fix bugs
This commit is contained in:
Chenggang Zhao
2025-06-11 15:48:18 +08:00
committed by GitHub
parent dd13c7145c
commit b8d90fb753
16 changed files with 413 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
csrc/kernels/configs.cuh
View File

@@ -37,11 +37,25 @@
#undef __CUDA_NO_BFLOAT162_OPERATORS__
#endif
#include <cstdint>
#include <cuda_bf16.h>
#include <cuda_fp8.h>
#include <cuda_runtime.h>
#ifndef DISABLE_SM90_FEATURES
#include <cuda_fp8.h>
#else
// Ampere does not support FP8 features
#define __NV_E4M3 0
#define __NV_E5M2 1
typedef int __nv_fp8_interpretation_t;
typedef int __nv_fp8x4_e4m3;
typedef uint8_t __nv_fp8_storage_t;
#endif
#ifndef DISABLE_NVSHMEM
#include <nvshmem.h>
#include <nvshmemx.h>
#include <infiniband/mlx5dv.h>
#include <non_abi/device/threadgroup/nvshmemi_common_device_defines.cuh>
#include <device_host_transport/nvshmem_common_ibgda.h>
#endif