foundation-model-stack / fms-extras

Related projects: ⓘ

• rayleizhu / vllm-ra
  [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
  ☆29Updated 6 months ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"
  ☆57Updated 5 months ago
• Ryu1845 / hyena-jax
  Implementation of Hyena Hierarchy in JAX
  ☆10Updated last year
• google-deepmind / asyncdiloco
  ☆38Updated 8 months ago
• fw-ai / llama-cuda-graph-example
  Example of applying CUDA graphs to LLaMA-v2
  ☆10Updated last year
• apple / ml-recurrent-drafter
  ☆61Updated 3 weeks ago
• aredden / torch-cublas-hgemm
  PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
  ☆25Updated 3 weeks ago
• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆36Updated 8 months ago
• tridao / flash-attention-wheels
  ☆38Updated 9 months ago
• CerebrasResearch / Sparse-IFT
  Official repository of Sparse ISO-FLOP Transformations for Maximizing Training Efficiency
  ☆23Updated last month
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆66Updated 7 months ago
• Infini-AI-Lab / MagicDec
  Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆55Updated this week
• tanyuqian / redco
  NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference
  ☆58Updated this week
• mobiusml / gemlite
  Simple and fast low-bit matmul kernels in CUDA
  ☆48Updated this week
• wdlctc / mini-s
  ☆26Updated this week
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆94Updated 2 weeks ago
• IST-DASLab / MicroAdam
  This repository contains code for the MicroAdam paper.
  ☆9Updated 2 months ago
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆34Updated 2 months ago
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆56Updated last week
• mgmalek / efficient_cross_entropy
  ☆66Updated 3 months ago
• IST-DASLab / QIGen
  Repository for CPU Kernel Generation for LLM Inference
  ☆25Updated last year
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆47Updated 2 weeks ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆46Updated 9 months ago
• shadowpa0327 / Palu
  Code for Palu: Compressing KV-Cache with Low-Rank Projection
  ☆39Updated this week
• tobiaskatsch / GatedLinearRNN
  ☆23Updated 6 months ago
• RobertCsordas / moeut
  ☆50Updated last month
• facebookresearch / adaptive_scheduling
  Experimental scripts for researching data adaptive learning rate scheduling.
  ☆23Updated 11 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆55Updated 4 months ago
• IST-DASLab / peft-rosa
  A fork of the PEFT library, supporting Robust Adaptation (RoSA)
  ☆13Updated last month
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆29Updated 3 weeks ago