Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
☆2,766Jun 25, 2024Updated 2 years ago
Alternatives and similar repositories for Medusa
Users that are interested in Medusa are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,341Mar 6, 2025Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,499Feb 20, 2026Updated 5 months ago
- Fast inference from large lauguage models via speculative decoding☆924Aug 22, 2024Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,898Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,227Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,615Jul 17, 2025Updated last year
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,263Jul 11, 2024Updated 2 years ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆220Mar 5, 2026Updated 5 months ago
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,393Updated this week
- Fast and memory-efficient exact attention☆24,716Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,172May 8, 2024Updated 2 years ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆404Apr 22, 2025Updated last year
- Transformer related optimization, including BERT, GPT☆6,445Mar 27, 2024Updated 2 years ago
- FlashInfer: Kernel Library for LLM Serving☆6,172Updated this week
- 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.
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,290Jun 27, 2026Updated last month
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆8,009Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆853Mar 6, 2025Updated last year
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,922Jan 21, 2024Updated 2 years ago
- Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)☆2,688Aug 14, 2024Updated 2 years ago
- Large Language Model Text Generation Inference☆10,886Mar 21, 2026Updated 4 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,675Jul 12, 2024Updated 2 years ago
- Accessible large language models via k-bit quantization for PyTorch.☆8,413Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,072Apr 11, 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.
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,109Jun 30, 2025Updated last year
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,245Aug 22, 2025Updated 11 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,226Apr 8, 2026Updated 4 months ago
- Tools for merging pretrained large language models.☆7,291Jun 17, 2026Updated 2 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,349May 11, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,129Sep 4, 2024Updated last year
- Ongoing research training transformer models at scale☆17,449Updated this week
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆280Aug 31, 2024Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,352Mar 27, 2024Updated 2 years 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.
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,991Jun 10, 2024Updated 2 years ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,907Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,453Updated this week
- A framework for few-shot evaluation of language models.☆13,663Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,358Oct 28, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆975Mar 29, 2026Updated 4 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,492Updated this week