Ascend / torchairLinks
☆18Updated this week
Alternatives and similar repositories for torchair
Users that are interested in torchair are comparing it to the libraries listed below
Sorting:
- GPTQ inference TVM kernel☆40Updated last year
- ☆92Updated 5 months ago
- Tile-based language built for AI computation across all scales☆47Updated this week
- ☆63Updated 4 months ago
- ☆98Updated 11 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆67Updated this week
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 11 months ago
- DeeperGEMM: crazy optimized version☆70Updated 3 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆112Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆107Updated 3 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated 2 months ago
- A lightweight design for computation-communication overlap.☆160Updated last week
- A practical way of learning Swizzle☆25Updated 6 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Updated last month
- ☆74Updated 5 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 7 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆81Updated 2 weeks ago
- A simple calculation for LLM MFU.☆44Updated 5 months ago
- ☆19Updated 11 months ago
- ☆92Updated 3 months ago
- ☆84Updated this week
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 6 months ago
- Fast and memory-efficient exact attention☆91Updated this week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆105Updated 3 months ago
- Implement Flash Attention using Cute.☆95Updated 8 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- ☆146Updated 5 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆46Updated 2 weeks ago
- TensorRT LLM Benchmark Configuration☆13Updated last year