☆223Jan 23, 2025Updated last year
Alternatives and similar repositories for ml-recurrent-drafter
Users that are interested in ml-recurrent-drafter are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆396Apr 22, 2025Updated last year
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆278Aug 31, 2024Updated last year
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆28Apr 15, 2025Updated last year
- ☆93Aug 18, 2024Updated last year
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆15Apr 30, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- JAX Scalify: end-to-end scaled arithmetics☆18Oct 30, 2024Updated last year
- An Extensible Deep Learning Library☆2,360May 16, 2026Updated 2 weeks ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,743Jun 25, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆961Mar 29, 2026Updated 2 months ago
- ☆15Mar 2, 2025Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆276Oct 3, 2025Updated 7 months ago
- ☆138May 29, 2025Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,357Feb 20, 2026Updated 3 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆542Feb 10, 2025Updated last year
- 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.
- Odysseus: Playground of LLM Sequence Parallelism☆78Jun 17, 2024Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆840Mar 6, 2025Updated last year
- ☆13Feb 5, 2024Updated 2 years ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆149Dec 4, 2024Updated last year
- ☆66Apr 26, 2025Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆219Mar 5, 2026Updated 2 months ago
- Multilingual Knowledge Graph Enhancement (EMNLP 2023)☆24Nov 28, 2023Updated 2 years ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆372Apr 13, 2026Updated last month
- Kaggle AIMO2 solution with token-efficient reasoning LLM recipes☆50Aug 7, 2025Updated 9 months ago
- 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.
- LLM Serving Performance Evaluation Harness☆84Feb 25, 2025Updated last year
- ☆165Feb 15, 2025Updated last year
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.☆103Jun 29, 2025Updated 11 months ago
- Official repo of dataset-decomposition paper [NeurIPS 2024]☆21Jan 8, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,214Apr 8, 2026Updated last month
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆12Jun 24, 2024Updated last year
- DLPack for Tensorflow☆34Apr 13, 2020Updated 6 years ago
- ☆47Jul 25, 2024Updated last year
- Tile primitives for speedy kernels☆3,377May 22, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- PyTorch native quantization and sparsity for training and inference☆2,834May 22, 2026Updated last week
- Open-source reproducible benchmarks from Argmax☆89Updated this week
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆92Jul 17, 2025Updated 10 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,297Updated this week
- ☆311Apr 23, 2025Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆670May 21, 2026Updated last week
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆21Jul 29, 2024Updated last year