Commit
·
97efda3
1
Parent(s):
2969437
update readme
Browse files
README.md
CHANGED
|
@@ -99,6 +99,14 @@ torchrun --nproc-per-node ${MP} generate.py --ckpt-path ${SAVE_PATH} --config ${
|
|
| 99 |
|
| 100 |
|
| 101 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
## License
|
| 103 |
|
| 104 |
This repository and the model weights are licensed under the [MIT License](LICENSE).
|
|
|
|
| 99 |
|
| 100 |
|
| 101 |
|
| 102 |
+
## Open-Source Kernels
|
| 103 |
+
|
| 104 |
+
For TileLang kernels with **better readability and research-purpose design**, please refer to [TileLang](https://github.com/tile-ai/tilelang/tree/main/examples/deepseek-v32).
|
| 105 |
+
|
| 106 |
+
For **high-performance CUDA kernels**, indexer logit kernels (including paged versions) are available in [DeepGEMM](https://github.com/deepseek-ai/DeepGEMM/pull/200). Sparse attention kernels are released in [FlashMLA](https://github.com/deepseek-ai/FlashMLA/pull/98).
|
| 107 |
+
|
| 108 |
+
|
| 109 |
+
|
| 110 |
## License
|
| 111 |
|
| 112 |
This repository and the model weights are licensed under the [MIT License](LICENSE).
|