leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

CUTLASS 3.7 (#2045)

Browse Source 
* CUTLASS 3.7

* clean up changelog

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-01-18 06:53:07 -08:00
committed by GitHub
parent 902dff3663
commit b78588d163
2030 changed files with 8947 additions and 3475 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
CHANGELOG.md
View File

@@ -1,4 +1,12 @@
# NVIDIA CUTLASS Changelog
## [3.7.0](https://github.com/NVIDIA/cutlass/releases/tag/v3.7.0) (2025-01-11)
- [Hopper blockwise scaling FP8 GEMM](./examples/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling.cu) uses 2D scaling tensor, assigning one value per threadblock. This allows a finer-grained scaling to be applied for each output tile per gemm-k iteration. The operands and scaling tensors are loaded from global memory to shared memory using TMA and cp_async, respectively. The scaling is applied inside the mainloop. Details with figures are [here](https://github.com/NVIDIA/cutlass/pull/1932#issue-2645398439).
- [Distributed GEMM](./examples/65_distributed_gemm/65_distributed_gemm.cu) is a new (experimental) API which can turn existing CUTLASS GEMM kernels into pipelined Tensor Parallel GEMMs that run efficiently on NVLink-based network of GPUs. Its pipelining schedules can hide most of the communication behind computation, and relies on point-to-point communication, which can simply use CUDA runtime's peer device access feature. It also utilizes remote TMA loads and memcopies with CUDA graphs to handle communication primarily through the Copy Engine, leaving all SMs free for Hopper's persistent kernels. For more details you can refer to the [DistGEMM blog post](https://blog.shi-labs.com/distributed-gemm-88be6a481e2b).
- Improved persistent grid launch for Hopper kernels with large cluster sizes (>= size of 4) using the new `make_kernel_hardware_info` API as shown in [example 48](./examples/48_hopper_warp_specialized_gemm/48_hopper_warp_specialized_gemm.cu).
- Enabled high precision accumulation for Hopper FP8 Sparse GEMM.
- Various improvements and fixes from the community and CUTLASS team. Thanks to everyone who submitted PRs!
- Optimal code generation with CUDA toolkit versions 12.6.
## [3.6.0](https://github.com/NVIDIA/cutlass/releases/tag/v3.6.0) (2024-10-03)
- [Hopper structured sparse GEMM](./examples/62_hopper_sparse_gemm/62_hopper_sparse_gemm.cu).
@@ -440,7 +448,7 @@
## Copyright
Copyright (c) 2017 - 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```