punica-ai / punicaLinks
Serving multiple LoRA finetuned LLM as one
☆1,131Updated last year
Alternatives and similar repositories for punica
Users that are interested in punica are comparing it to the libraries listed below
Sorting:
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,314Updated 10 months ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,885Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆978Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆936Updated 2 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,086Updated 6 months ago
- ☆584Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆711Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,171Updated 3 months ago
- A high-performance inference system for large language models, designed for production environments.☆489Updated 3 weeks ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆801Updated 10 months ago
- The Triton TensorRT-LLM Backend☆912Updated this week
- Microsoft Automatic Mixed Precision Library☆634Updated last month
- Official implementation of Half-Quadratic Quantization (HQQ)☆905Updated 3 weeks ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,854Updated this week
- YaRN: Efficient Context Window Extension of Large Language Models☆1,656Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,685Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆751Updated last year
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,300Updated 8 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆885Updated last month
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆863Updated last year
- Fast, Flexible and Portable Structured Generation☆1,464Updated this week
- scalable and robust tree-based speculative decoding algorithm☆366Updated 11 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,243Updated last year
- Large Context Attention☆759Updated 3 months ago
- batched loras☆347Updated 2 years ago
- ☆576Updated last year
- Latency and Memory Analysis of Transformer Models for Training and Inference☆475Updated 8 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆733Updated last year
- LLMPerf is a library for validating and benchmarking LLMs☆1,074Updated last year
- ☆551Updated last year