BlackSamorez / tensor_parallelLinks
Automatically split your PyTorch models on multiple GPUs for training & inference
☆656Updated 2 years ago
Alternatives and similar repositories for tensor_parallel
Users that are interested in tensor_parallel are comparing it to the libraries listed below
Sorting:
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,315Updated 11 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆639Updated last year
- Large Context Attention☆766Updated 3 months ago
- distributed trainer for LLMs☆588Updated last year
- Fast Inference Solutions for BLOOM☆566Updated last year
- Microsoft Automatic Mixed Precision Library☆635Updated 2 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆751Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆473Updated last year
- Scalable toolkit for efficient model alignment☆852Updated 4 months ago
- Official PyTorch implementation of QA-LoRA☆145Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆713Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,431Updated last year
- Code for the ALiBi method for transformer language models (ICLR 2022)☆549Updated 2 years ago
- Pipeline Parallelism for PyTorch☆784Updated last year
- ☆553Updated last year
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆654Updated last year
- Explorations into some recent techniques surrounding speculative decoding☆299Updated last year
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆549Updated 8 months ago
- Ring attention implementation with flash attention☆979Updated 4 months ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆865Updated last year
- Rectified Rotary Position Embeddings☆388Updated last year
- LOMO: LOw-Memory Optimization☆987Updated last year
- Official repository for LongChat and LongEval☆534Updated last year
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆224Updated 2 years ago
- Code used for sourcing and cleaning the BigScience ROOTS corpus☆318Updated 2 years ago
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆409Updated last year
- YaRN: Efficient Context Window Extension of Large Language Models☆1,664Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,005Updated last year
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆734Updated last year
- GPTQ inference Triton kernel☆321Updated 2 years ago