Alternatives and similar repositories for MELT-public

Users that are interested in MELT-public are comparing it to the libraries listed below

• UbiquitousLearning / MobileFM
  One-size-fits-all model for mobile AI, a novel paradigm for mobile AI in which the OS and hardware co-manage a foundation model that is c…
  ☆28Updated last year
• Nokia-Bell-Labs / salted-dnns
  (HotMobile'24) Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing
  ☆17Updated last year
• microsoft / glinthawk
  An LLM inference engine, written in C++
  ☆15Updated last month
• stevelaskaridis / awesome-mobile-llm
  Awesome Mobile LLMs
  ☆210Updated last week
• apple / pfl-research
  Simulation framework for accelerating research in Private Federated Learning
  ☆330Updated last month
• facebookresearch / MemoryMosaics
  Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.
  ☆46Updated 5 months ago
• pan-x-c / EE-LLM
  EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).
  ☆65Updated last year
• eth-easl / deltazip
  Compression for Foundation Models
  ☆33Updated 3 months ago
• pilancilab / caldera
  Compressing Large Language Models using Low Precision and Low Rank Decomposition
  ☆95Updated 7 months ago
• vcskaushik / LLMzip
  ☆57Updated 6 months ago
• Zyphra / zcookbook
  Training hybrid models for dummies.
  ☆25Updated 6 months ago
• yandex-research / swarm
  Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"
  ☆141Updated last year
• google-deepmind / asyncdiloco
  ☆45Updated last year
• mobiusml / aana_sdk
  Aana SDK is a powerful framework for building AI enabled multimodal applications.
  ☆49Updated this week
• ml-energy / leaderboard
  How much energy do GenAI models consume?
  ☆45Updated 2 months ago
• UNITES-Lab / MoE-Quantization
  Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"
  ☆21Updated 2 weeks ago
• UbiquitousLearning / Backpropagation_Free_Training_Survey
  ☆23Updated last year
• RWKV / RWKV-LM
  RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…
  ☆50Updated 4 months ago
• IST-DASLab / sparseprop
  ☆15Updated last year
• jeho-lee / Awesome-On-Device-AI-Systems
  ☆66Updated last month
• hpcgroup / loki
  Algorithms for approximate attention in LLMs
  ☆18Updated 3 months ago
• sebulo / LoQT
  ☆79Updated 8 months ago
• VITA-Group / LoCoCo
  [ICML‘2024] "LoCoCo: Dropping In Convolutions for Long Context Compression", Ruisi Cai, Yuandong Tian, Zhangyang Wang, Beidi Chen
  ☆17Updated 10 months ago
• CannyLab / anthology
  [EMNLP 2024 Main] Virtual Personas for Language Models via an Anthology of Backstories
  ☆29Updated 8 months ago
• hmarkc / parallel-prompt-decoding
  Efficient LLM Inference Acceleration using Prompting
  ☆48Updated 8 months ago
• AutonomicPerfectionist / PipeInfer
  PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
  ☆30Updated 8 months ago
• UCDvision / NOLA
  Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"
  ☆56Updated 10 months ago
• ScalingIntelligence / good-kernels
  Samples of good AI generated CUDA kernels
  ☆84Updated last month
• Lucky-Lance / Expert_Sparsity
  [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
  ☆94Updated last year
• NVlabs / MaskLLM
  [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models
  ☆171Updated 6 months ago