Dao-AILab / gemm-cublasLinks
β23Updated 6 months ago
Alternatives and similar repositories for gemm-cublas
Users that are interested in gemm-cublas are comparing it to the libraries listed below
Sorting:
- Odysseus: Playground of LLM Sequence Parallelismβ78Updated last year
- A bunch of kernels that might make stuff slower πβ64Updated this week
- An efficient implementation of the NSA (Native Sparse Attention) kernelβ124Updated 4 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizerβ206Updated 5 months ago
- β130Updated 5 months ago
- β50Updated 6 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of codeβ51Updated 4 months ago
- β109Updated 6 months ago
- The evaluation framework for training-free sparse attention in LLMsβ103Updated last month
- β254Updated 5 months ago
- β143Updated this week
- Quantized Attention on GPUβ44Updated last year
- β113Updated last year
- FlexAttention w/ FlashAttention3 Supportβ27Updated last year
- Awesome Triton Resourcesβ36Updated 6 months ago
- β95Updated 8 months ago
- Transformers components but in Tritonβ34Updated 6 months ago
- Experiment of using Tangent to autodiff tritonβ79Updated last year
- JAX bindings for Flash Attention v2β98Updated 2 weeks ago
- Framework to reduce autotune overhead to zero for well known deployments.β85Updated 2 months ago
- β57Updated last year
- ring-attention experimentsβ155Updated last year
- extensible collectives library in tritonβ91Updated 7 months ago
- β22Updated 8 months ago
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin toβ¦β25Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsityβ85Updated last year
- Benchmark tests supporting the TiledCUDA library.β17Updated last year
- β32Updated last year
- Linear Attention Sequence Parallelism (LASP)β87Updated last year
- CUDA and Triton implementations of Flash Attention with SoftmaxN.β73Updated last year