Alternatives and similar repositories for assignment2-systems

Users that are interested in assignment2-systems are comparing it to the libraries listed below

• hao-ai-lab / cse234-w25-PA
  ☆41Updated 8 months ago
• stanford-cs336 / assignment5-alignment
  ☆71Updated 3 months ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆302Updated 2 weeks ago
• hkproj / triton-flash-attention
  ☆216Updated 10 months ago
• evintunador / triton_docs_tutorials
  making the official triton tutorials actually comprehensible
  ☆61Updated 2 months ago
• NVIDIA / Star-Attention
  Efficient LLM Inference over Long Sequences
  ☆390Updated 4 months ago
• huggingface / picotron_tutorial
  ☆225Updated 3 weeks ago
• Infini-AI-Lab / MagicPIG
  [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation
  ☆240Updated 11 months ago
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆102Updated last month
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆210Updated 8 months ago
• gpu-mode / ring-attention
  ring-attention experiments
  ☆155Updated last year
• gpu-mode / triton-index
  Cataloging released Triton kernels.
  ☆265Updated 2 months ago
• mingyin0312 / RLFromScratch
  ☆451Updated 2 months ago
• RLsys-Foundation / TritonForge
  🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…
  ☆98Updated last week
• NVIDIA / kvpress
  LLM KV cache compression made easy
  ☆680Updated last week
• ScalingIntelligence / KernelBench
  KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs)
  ☆655Updated last week
• tilde-research / nsa-impl
  An efficient implementation of the NSA (Native Sparse Attention) kernel
  ☆124Updated 4 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆223Updated last week
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆367Updated 2 months ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆145Updated 8 months ago
• PluralisResearch / AsyncPP
  Asynchronous pipeline parallel optimization
  ☆18Updated 5 months ago
• arpita8 / Awesome-Mixture-of-Experts-Papers
  Survey: A collection of AWESOME papers and resources on the latest research in Mixture of Experts.
  ☆138Updated last year
• CASE-Lab-UMD / Unified-MoE-Compression
  The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
  ☆80Updated 7 months ago
• 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
• sgl-project / sglang-jax
  JAX backend for SGL
  ☆163Updated this week
• Dao-AILab / grouped-latent-attention
  ☆130Updated 5 months ago
• thu-nics / MoA
  [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
  ☆150Updated 4 months ago
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆247Updated 5 months ago
• gpu-mode / profiling-cuda-in-torch
  ☆177Updated last year
• tspeterkim / paged-attention-minimal
  a minimal cache manager for PagedAttention, on top of llama3.
  ☆125Updated last year