ZRayZzz / flash-attention-v100Links
☆53Updated last year
Alternatives and similar repositories for flash-attention-v100
Users that are interested in flash-attention-v100 are comparing it to the libraries listed below
Sorting:
- Triton Documentation in Chinese Simplified / Triton 中文文档☆82Updated 5 months ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆218Updated last month
- ☆79Updated last year
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆106Updated 2 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆113Updated last year
- ☆61Updated last week
- ☆143Updated 2 months ago
- UltraScale Playbook 中文版☆74Updated 6 months ago
- Implement custom operators in PyTorch with cuda/c++☆71Updated 2 years ago
- 使用 CUDA C++ 实现的 llama 模型推理框 架☆62Updated 10 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆264Updated last month
- Tutorials for writing high-performance GPU operators in AI frameworks.☆131Updated 2 years ago
- ☆141Updated last year
- 注释的nano_vllm仓库,并且完成了MiniCPM4的适配以及注册新模型的功能☆69Updated last month
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆130Updated this week
- ☆50Updated 10 months ago
- ☆147Updated 6 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆192Updated this week
- simplify >2GB large onnx model☆63Updated 9 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆106Updated 5 months ago
- ☆128Updated 8 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆354Updated this week
- Efficient Mixture of Experts for LLM Paper List☆127Updated this week
- ☆98Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆278Updated last year
- DeepSeek Native Sparse Attention pytorch implementation☆95Updated last month
- ☆95Updated 5 months ago
- qwen-nsa☆74Updated 5 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆70Updated 3 months ago
- ☆42Updated last year