tile-ai / TileAttentionLinks
☆39Updated this week
Alternatives and similar repositories for TileAttention
Users that are interested in TileAttention are comparing it to the libraries listed below
Sorting:
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- ☆49Updated last month
- Quantized Attention on GPU☆44Updated 7 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- ☆71Updated last month
- Benchmark tests supporting the TiledCUDA library.☆16Updated 7 months ago
- ☆22Updated last year
- ☆31Updated last year
- Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.☆21Updated 2 weeks ago
- Vocabulary Parallelism☆19Updated 3 months ago
- ☆19Updated 8 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- GPTQ inference TVM kernel☆40Updated last year
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆19Updated this week
- Transformers components but in Triton☆34Updated last month
- ☆21Updated last month
- ☆60Updated 2 months ago
- FlexAttention w/ FlashAttention3 Support☆26Updated 8 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated 11 months ago
- ☆21Updated 3 months ago
- A simple calculation for LLM MFU.☆38Updated 3 months ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 4 years ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆48Updated 2 years ago
- 方便扩展的Cuda算子理解和优化框架,仅用在学习使用☆15Updated last year
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆23Updated this week
- patches for huggingface transformers to save memory☆23Updated 3 weeks ago
- DeeperGEMM: crazy optimized version☆69Updated last month
- Estimate MFU for DeepSeekV3☆24Updated 5 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated 2 weeks ago
- ☆39Updated last year