36
36
| [[ LLM推理优化] [ Weight Only ] 📖WINT8/4-(02): 快速反量化之INT8转BF16] ( https://zhuanlan.zhihu.com/p/657073159 ) | @DefTruth |
37
37
| [[ LLM推理优化] [ Weight Only ] 📖WINT8/4-(03): LOP3指令详解及INT4转FP16/BF16] ( https://zhuanlan.zhihu.com/p/657073857 ) | @DefTruth |
38
38
| [[ LLM推理优化] [ LLM Infra整理 ] 📖100+篇: 大模型推理各方向新发展整理] ( https://zhuanlan.zhihu.com/p/693680304 ) | @DefTruth |
39
- | [[ LLM推理优化] [ LLM Infra整理 ] 📖30+篇: LLM推理论文集-500页PDF💡 ] ( https://zhuanlan.zhihu.com/p/669777159 ) | @DefTruth |
39
+ | [[ LLM推理优化] [ LLM Infra整理 ] 📖30+篇: LLM推理论文集-500页PDF] ( https://zhuanlan.zhihu.com/p/669777159 ) | @DefTruth |
40
40
| [[ LLM推理优化] [ LLM Infra整理 ] 📖FlashDecoding++: 比FlashDecoding还要快!] ( https://zhuanlan.zhihu.com/p/665022589 ) | @DefTruth |
41
41
| [[ LLM推理优化] [ LLM Infra整理 ] 📖TensorRT-LLM开源,TensorRT 9.1也来了] ( https://zhuanlan.zhihu.com/p/662361469 ) | @DefTruth |
42
- | [[ LLM推理优化] [ LLM Infra整理 ] 📖20+篇: LLM推理论文集-300页PDF💡 ] ( https://zhuanlan.zhihu.com/p/658091768 ) | @DefTruth |
42
+ | [[ LLM推理优化] [ LLM Infra整理 ] 📖20+篇: LLM推理论文集-300页PDF] ( https://zhuanlan.zhihu.com/p/658091768 ) | @DefTruth |
43
43
| [[ LLM推理优化] [ LLM Infra整理 ] 📖PagedAttention论文新鲜出炉] ( https://zhuanlan.zhihu.com/p/617015570 ) | @DefTruth |
44
44
45
45
48
48
| 📖 类型-标题| 📖 作者|
49
49
| :---| :---|
50
50
| [[ 推理部署] [ CV/NLP ] 📖FastDeploy三行代码搞定150+ CV、NLP模型部署] ( https://zhuanlan.zhihu.com/p/581326442 ) | @DefTruth |
51
- | [[ 推理部署] [ CV ] 📖如何在lite.ai.toolkit(3.6k+🔥 stars)中增加您的模型?] ( https://zhuanlan.zhihu.com/p/523876625 ) | @DefTruth |
51
+ | [[ 推理部署] [ CV ] 📖如何在lite.ai.toolkit(3.6k+ stars)中增加您的模型?] ( https://zhuanlan.zhihu.com/p/523876625 ) | @DefTruth |
52
52
| [[ 推理部署] [ CV ] 📖美团 YOLOv6 ORT/MNN/TNN/NCNN C++推理部署] ( https://zhuanlan.zhihu.com/p/533643238 ) | @DefTruth |
53
53
| [[ 推理部署] [ ONNX ] 📖ONNX推理加速技术文档-杂记] ( https://zhuanlan.zhihu.com/p/524023964 ) | @DefTruth |
54
54
| [[ 推理部署] [ TensorFlow ] 📖Mac源码编译TensorFlow C++指北] ( https://zhuanlan.zhihu.com/p/524013615 ) | @DefTruth |
222
222
## ©️License
223
223
GNU General Public License v3.0
224
224
225
- ## 🎉 Contribute
226
- 🌟 如果觉得有用,不妨给个🌟👆🏻Star支持一下吧~
225
+ ## Contribute
226
+ 如果觉得有用,不妨给个🌟👆🏻Star支持一下吧~
227
227
228
228
<div align =' center ' >
229
229
<a href =" https://star-history.com/#DefTruth/CUDA-Learn-Notes&Date " >
@@ -243,5 +243,6 @@ GNU General Public License v3.0
243
243
- [ tiny-flash-attention] ( https://github.com/66RING/tiny-flash-attention )
244
244
- [ cute-gemm] ( https://github.com/reed-lau/cute-gemm )
245
245
- [ cutlass_flash_atten_fp8] ( https://github.com/weishengying/cutlass_flash_atten_fp8 )
246
+ - [ cuda_learning] ( https://github.com/ifromeast/cuda_learning )
246
247
247
248
</details >
0 commit comments