kyegomez / FlashAttention20Triton
Triton implementation of Flash Attention2.0
☆22Updated last year
Related projects ⓘ
Alternatives and complementary repositories for FlashAttention20Triton
- Odysseus: Playground of LLM Sequence Parallelism☆57Updated 5 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆38Updated 10 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆34Updated 8 months ago
- Implementation of Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting☆44Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆147Updated 4 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆49Updated 3 weeks ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆32Updated 3 months ago
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆195Updated 3 months ago
- ☆88Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆63Updated last week
- The official code for paper "parallel speculative decoding with adaptive draft length."☆24Updated 2 months ago
- An algorithm for static activation quantization of LLMs☆77Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆68Updated 4 months ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆33Updated 5 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆22Updated 9 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆42Updated 7 months ago
- ☆64Updated 3 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- AFPQ code implementation☆18Updated last year
- Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆74Updated 5 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated this week
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 11 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆38Updated last month
- ☆188Updated 6 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆19Updated 2 months ago
- Multi-Candidate Speculative Decoding☆28Updated 6 months ago
- ☆42Updated 6 months ago