☆20Dec 24, 2024Updated last year
Alternatives and similar repositories for flash_tree_attn
Users that are interested in flash_tree_attn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- triton ver of gqa flash attn, based on the tutorial☆12Aug 4, 2024Updated 2 years ago
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆22Apr 22, 2025Updated last year
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆86Jul 14, 2025Updated last year
- ☆22Nov 6, 2025Updated 9 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆55Jul 15, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆53May 12, 2026Updated 3 months ago
- An implementation of the Prism layer (https://arxiv.org/abs/2011.04823)☆12Nov 13, 2020Updated 5 years ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆48Jun 11, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- ☆65Apr 26, 2025Updated last year
- Code for Draft Attention☆103May 22, 2025Updated last year
- ☆23Aug 14, 2024Updated 2 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆154May 29, 2025Updated last year
- ☆32May 26, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆176Feb 27, 2026Updated 6 months ago
- ☆13Jan 7, 2025Updated last year
- [WIP] Better (FP8) attention for Hopper☆33Aug 21, 2026Updated last week
- Code for the papers: "Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach", "A Meta-Learning Approach for Gra…☆18Apr 26, 2022Updated 4 years ago
- ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs☆17Oct 24, 2025Updated 10 months ago
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)☆47Dec 9, 2023Updated 2 years ago
- [AACL 2023] Official implementation of paper "Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompti…☆21Apr 1, 2024Updated 2 years ago
- VibeRL is a Reinforcement Learning framework built essentially through vibe coding with Kimi K2.☆18Aug 24, 2026Updated last week
- official code for GliDe with a CaPE☆21Aug 13, 2024Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Official repository of "Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions", ICLR 2024 Sp…☆21Mar 7, 2024Updated 2 years ago
- 🔥LongCat-Video 1.7x🎉 speedup: cache acceleration and 4/8-bits weight only.☆15Oct 28, 2025Updated 10 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated last year
- Official Implement for Paper "Neural Krylov Iteration for Accelerating Linear System Solving"☆17May 6, 2025Updated last year
- The official code repo and data hub of top_nsigma sampling strategy for LLMs.☆28Feb 11, 2025Updated last year
- Official repository Flash Local Linear Attention☆39May 28, 2026Updated 3 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Jul 17, 2026Updated last month
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆22Sep 10, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Awesome code, projects, books, etc. related to CUDA☆40Aug 9, 2026Updated 3 weeks ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆157Dec 4, 2024Updated last year
- Website for CSE 234, Winter 2025☆16Mar 24, 2025Updated last year
- The code of paper "Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction" in NeurIPS 2023.☆14Nov 25, 2023Updated 2 years ago
- ☆170Feb 15, 2025Updated last year
- [NeurIPS 2025] Official PyTorch implementation for the paper AutoJudge: Judge Decoding Without Manual Annotation☆21Dec 22, 2025Updated 8 months ago
- [ICCV 2023] Multi-Label Knowledge Distillation☆32Apr 24, 2024Updated 2 years ago