graphcore-research / unit-scaling-demoLinks
Unit Scaling demo and experimentation code
☆16Updated last year
Alternatives and similar repositories for unit-scaling-demo
Users that are interested in unit-scaling-demo are comparing it to the libraries listed below
Sorting:
- Repository for CPU Kernel Generation for LLM Inference☆26Updated 2 years ago
- QuIP quantization☆54Updated last year
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- This repository contains code for the MicroAdam paper.☆20Updated 7 months ago
- ☆22Updated last year
- Implementation of Hyena Hierarchy in JAX☆10Updated 2 years ago
- FlexAttention w/ FlashAttention3 Support☆26Updated 9 months ago
- Make triton easier☆47Updated last year
- ☆74Updated 3 months ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated 9 months ago
- Linear Attention Sequence Parallelism (LASP)☆85Updated last year
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆18Updated last month
- ACL 2023☆39Updated 2 years ago
- The evaluation framework for training-free sparse attention in LLMs☆83Updated 3 weeks ago
- Awesome Triton Resources☆32Updated 2 months ago
- FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation☆49Updated last year
- ☆26Updated last year
- PB-LLM: Partially Binarized Large Language Models☆152Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆77Updated last year
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆48Updated 2 years ago
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆66Updated 7 months ago
- ☆51Updated last year
- ☆26Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 10 months ago
- ☆14Updated this week
- Here we will test various linear attention designs.☆60Updated last year
- Low-Rank Llama Custom Training☆23Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 9 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆109Updated 9 months ago