BlackSamorez / tensor_parallel
Automatically split your PyTorch models on multiple GPUs for training & inference
☆643Updated last year
Alternatives and similar repositories for tensor_parallel:
Users that are interested in tensor_parallel are comparing it to the libraries listed below
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,179Updated 3 months ago
- Large Context Attention☆670Updated 5 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆578Updated 10 months ago
- Microsoft Automatic Mixed Precision Library☆549Updated 3 months ago
- distributed trainer for LLMs☆555Updated 7 months ago
- Pipeline Parallelism for PyTorch☆736Updated 4 months ago
- Fast Inference Solutions for BLOOM☆563Updated 3 months ago
- Ring attention implementation with flash attention☆645Updated 3 weeks ago
- Official PyTorch implementation of QA-LoRA☆122Updated 10 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆400Updated 2 weeks ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆492Updated 2 months ago
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆439Updated 8 months ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆912Updated 2 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆680Updated 4 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆687Updated 3 months ago
- ☆537Updated last month
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,354Updated 9 months ago
- Fast inference from large lauguage models via speculative decoding☆630Updated 4 months ago
- Serving multiple LoRA finetuned LLM as one☆1,012Updated 8 months ago
- Minimalistic large language model 3D-parallelism training☆1,386Updated this week
- Scalable toolkit for efficient model alignment☆674Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,316Updated 6 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆667Updated 5 months ago
- ☆310Updated 9 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆212Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆692Updated 3 months ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆759Updated 4 months ago
- Explorations into some recent techniques surrounding speculative decoding☆229Updated 3 weeks ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,998Updated 9 months ago