Alternatives and similar repositories for AI-research-papers-pseudo-code

Users that are interested in AI-research-papers-pseudo-code are comparing it to the libraries listed below

• jaymody / speculative-sampling
  Simple implementation of Speculative Sampling in NumPy for GPT-2.
  ☆98Updated 2 years ago
• lucidrains / speculative-decoding
  Explorations into some recent techniques surrounding speculative decoding
  ☆288Updated 10 months ago
• anyscale / llm-continuous-batching-benchmarks
  ☆121Updated last year
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆60Updated last year
• meta-pytorch / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆301Updated 2 months ago
• NetEase-FuXi / EETQ
  Easy and Efficient Quantization for Transformers
  ☆202Updated 4 months ago
• tspeterkim / paged-attention-minimal
  a minimal cache manager for PagedAttention, on top of llama3.
  ☆125Updated last year
• gpu-mode / triton-index
  Cataloging released Triton kernels.
  ☆264Updated last month
• gnovack / distributed-training-and-deepspeed
  ☆17Updated 2 years ago
• cli99 / llm-analysis
  Latency and Memory Analysis of Transformer Models for Training and Inference
  ☆461Updated 6 months ago
• huggingface / picotron_tutorial
  ☆225Updated 2 weeks ago
• gpu-mode / ring-attention
  ring-attention experiments
  ☆155Updated last year
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆216Updated this week
• qhliu26 / Dive-into-Big-Model-Training
  📑 Dive into Big Model Training
  ☆114Updated 2 years ago
• haochengxi / Train_Transformers_with_INT4
  ☆156Updated 2 years ago
• meta-pytorch / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆223Updated last year
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆147Updated last year
• dropbox / gemlite
  Fast low-bit matmul kernels in Triton
  ☆388Updated last week
• mgmalek / efficient_cross_entropy
  ☆121Updated last year
• open-lm-engine / accelerated-model-architectures
  A bunch of kernels that might make stuff slower 😉
  ☆64Updated this week
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆247Updated last month
• foundation-model-stack / fms-fsdp
  🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…
  ☆270Updated 3 months ago
• epfml / dynamic-sparse-flash-attention
  ☆149Updated 2 years ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆323Updated last year
• gpu-mode / profiling-cuda-in-torch
  ☆174Updated last year
• Deep-Learning-Profiling-Tools / triton-viz
  ☆246Updated this week
• nbasyl / LLM-FP4
  The official implementation of the EMNLP 2023 paper LLM-FP4
  ☆217Updated last year
• melisa-writer / short-transformers
  Prune transformer layers
  ☆69Updated last year
• SqueezeAILab / KVQuant
  [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  ☆389Updated last year
• zinccat / Awesome-Triton-Kernels
  Collection of kernels written in Triton language
  ☆159Updated 7 months ago