databricks / megablocks
☆1,164Updated last week
Related projects: ⓘ
- Minimalistic large language model 3D-parallelism training☆1,111Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,099Updated 7 months ago
- Serving multiple LoRA finetuned LLM as one☆946Updated 4 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,352Updated 6 months ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,698Updated 7 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,333Updated 2 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,306Updated 5 months ago
- Scalable toolkit for efficient model alignment☆509Updated this week
- Transformers with Arbitrarily Large Context☆613Updated last month
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,624Updated this week
- distributed trainer for LLMs☆521Updated 3 months ago
- Official Implementation of EAGLE-1 and EAGLE-2☆747Updated 3 weeks ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆606Updated last month
- A simple and effective LLM pruning approach.☆614Updated last month
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆629Updated last month
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,843Updated last week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,206Updated 2 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,021Updated 8 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,138Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆659Updated this week
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆694Updated 3 weeks ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,180Updated 2 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,875Updated 5 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆1,935Updated last week
- LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processin…☆659Updated this week
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆657Updated 5 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆672Updated last month
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆451Updated last month
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆539Updated 6 months ago
- ☆520Updated 8 months ago