FlagOpen / FlagCXLinks
☆66Updated last week
Alternatives and similar repositories for FlagCX
Users that are interested in FlagCX are comparing it to the libraries listed below
Sorting:
- A lightweight design for computation-communication overlap.☆141Updated last week
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆79Updated last month
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆87Updated last month
- ☆58Updated 7 months ago
- ☆77Updated last month
- ☆148Updated 5 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆246Updated last week
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 9 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated 3 weeks ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 4 months ago
- Examples of CUDA implementations by Cutlass CuTe☆195Updated 4 months ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- ☆122Updated 6 months ago
- A tutorial for CUDA&PyTorch☆144Updated 5 months ago
- ☆29Updated 4 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆70Updated 10 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆38Updated 3 months ago
- ☆96Updated 9 months ago
- PyTorch distributed training acceleration framework☆49Updated 4 months ago
- ☆36Updated 8 months ago
- DeepSeek-V3/R1 inference performance simulator☆148Updated 2 months ago
- ☆139Updated last year
- ☆34Updated last year
- Optimize softmax in triton in many cases☆21Updated 9 months ago
- Implement Flash Attention using Cute.☆87Updated 6 months ago
- Optimize GEMM with tensorcore step by step☆26Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆126Updated 2 months ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆58Updated 7 months ago
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆96Updated last week
- ☆60Updated last month