vllm-project / flash-attentionLinks
Fast and memory-efficient exact attention
☆87Updated last week
Alternatives and similar repositories for flash-attention
Users that are interested in flash-attention are comparing it to the libraries listed below
Sorting:
- ☆92Updated 4 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆111Updated last year
- A lightweight design for computation-communication overlap.☆155Updated last week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆104Updated 3 months ago
- ☆97Updated 11 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆100Updated 3 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆257Updated this week
- ☆145Updated 5 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆261Updated last month
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆313Updated this week
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago
- ☆61Updated 3 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆407Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆109Updated 2 months ago
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆64Updated this week
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆211Updated 2 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆277Updated last year
- Standalone Flash Attention v2 kernel without libtorch dependency☆111Updated 11 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 6 months ago
- ☆279Updated last week
- Pipeline Parallelism Emulation and Visualization☆60Updated 2 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆204Updated last week
- A low-latency & high-throughput serving engine for LLMs☆405Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- ☆86Updated 9 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆66Updated 2 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 2 weeks ago
- ☆195Updated 3 months ago
- Implement Flash Attention using Cute.☆94Updated 8 months ago