FlagTree / flagtreeLinks
FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.
☆65Updated this week
Alternatives and similar repositories for flagtree
Users that are interested in flagtree are comparing it to the libraries listed below
Sorting:
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 6 months ago
- ☆149Updated 6 months ago
- ☆89Updated 2 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆111Updated 10 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆93Updated 2 weeks ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆58Updated 8 months ago
- ☆96Updated 10 months ago
- ☆80Updated last week
- ☆102Updated 4 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆74Updated 11 months ago
- ☆137Updated last year
- play gemm with tvm☆91Updated 2 years ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆95Updated 7 years ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆91Updated 2 months ago
- A home for the final text of all TVM RFCs.☆105Updated 10 months ago
- Assembler and Decompiler for NVIDIA (Maxwell Pascal Volta Turing Ampere) GPUs.☆81Updated 2 years ago
- ☆37Updated last year
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆254Updated last month
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆103Updated 2 months ago
- A practical way of learning Swizzle☆22Updated 6 months ago
- ☆126Updated 2 months ago
- ☆139Updated last year
- ☆149Updated 7 months ago
- ☆246Updated last month
- Optimize GEMM with tensorcore step by step☆31Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆91Updated last month
- ⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA.🎉☆194Updated 2 months ago
- A lightweight design for computation-communication overlap.☆154Updated last month
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆63Updated 10 months ago
- ☆30Updated 4 months ago