foundation-model-stack / fms-extras
☆17Updated last week
Related projects: ⓘ
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆29Updated 6 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆57Updated 5 months ago
- Implementation of Hyena Hierarchy in JAX☆10Updated last year
- ☆38Updated 8 months ago
- Example of applying CUDA graphs to LLaMA-v2☆10Updated last year
- ☆61Updated 3 weeks ago
- PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu☆25Updated 3 weeks ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆36Updated 8 months ago
- ☆38Updated 9 months ago
- Official repository of Sparse ISO-FLOP Transformations for Maximizing Training Efficiency☆23Updated last month
- Experiment of using Tangent to autodiff triton☆66Updated 7 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆55Updated this week
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆58Updated this week
- Simple and fast low-bit matmul kernels in CUDA☆48Updated this week
- ☆26Updated this week
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆94Updated 2 weeks ago
- This repository contains code for the MicroAdam paper.☆9Updated 2 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆34Updated 2 months ago
- Utilities for Training Very Large Models☆56Updated last week
- ☆66Updated 3 months ago
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆47Updated 2 weeks ago
- Triton Implementation of HyperAttention Algorithm☆46Updated 9 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆39Updated this week
- ☆23Updated 6 months ago
- ☆50Updated last month
- Experimental scripts for researching data adaptive learning rate scheduling.☆23Updated 11 months ago
- Here we will test various linear attention designs.☆55Updated 4 months ago
- A fork of the PEFT library, supporting Robust Adaptation (RoSA)☆13Updated last month
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆29Updated 3 weeks ago