Alternatives and similar repositories for tiny-llm

Users that are interested in tiny-llm are comparing it to the libraries listed below

• sgl-project / mini-sglang
  A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
  ☆3,067Updated this week
• zhaochenyang20 / Awesome-ML-SYS-Tutorial
  My learning notes for ML SYS.
  ☆5,077Updated last week
• stanford-cs336 / spring2025-lectures
  ☆2,457Updated 2 weeks ago
• GeeeekExplorer / nano-vllm
  Nano vLLM
  ☆10,892Updated 2 months ago
• stanford-cs336 / assignment1-basics
  Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
  ☆1,138Updated 4 months ago
• tile-ai / tilelang
  Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
  ☆4,739Updated last week
• policy-gradient / GRPO-Zero
  Implementing DeepSeek R1's GRPO algorithm from scratch
  ☆1,747Updated 9 months ago
• AmberLJC / LLMSys-PaperList
  Large Language Model (LLM) Systems Paper List
  ☆1,765Updated last week
• LMCache / LMCache
  Supercharge Your LLM with the Fastest KV Cache Layer
  ☆6,750Updated this week
• THUDM / slime
  slime is an LLM post-training framework for RL Scaling.
  ☆3,466Updated this week
• kvcache-ai / Mooncake
  Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
  ☆4,600Updated this week
• natolambert / rlhf-book
  Textbook on reinforcement learning from human feedback
  ☆1,426Updated this week
• mirage-project / mirage
  Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
  ☆2,084Updated 2 weeks ago
• ai-dynamo / dynamo
  A Datacenter Scale Distributed Inference Serving Framework
  ☆5,793Updated last week
• deepseek-ai / open-infra-index
  Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
  ☆7,957Updated 8 months ago
• therealoliver / Deepdive-llama3-from-scratch
  Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
  ☆618Updated 11 months ago
• flashinfer-ai / flashinfer
  FlashInfer: Kernel Library for LLM Serving
  ☆4,707Updated this week
• xlite-dev / LeetCUDA
  📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
  ☆9,382Updated 2 weeks ago
• gpu-mode / awesomeMLSys
  An ML Systems Onboarding list
  ☆972Updated last year
• huggingface / picotron
  Minimalistic 4D-parallelism distributed training framework for education purpose
  ☆1,991Updated 4 months ago
• xlite-dev / Awesome-LLM-Inference
  📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
  ☆4,936Updated last week
• yassa9 / qwen600
  Static suckless single batch CUDA-only qwen3-0.6B mini inference engine
  ☆539Updated 4 months ago
• openai / harmony
  Renderer for the harmony response format to be used with gpt-oss
  ☆4,146Updated last month
• vllm-project / production-stack
  vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
  ☆2,108Updated last week
• andrewkchan / yalm
  Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
  ☆550Updated 4 months ago
• PaddleJitLab / CUDATutorial
  A self-learning tutorail for CUDA High Performance Programing.
  ☆854Updated last week
• skyzh / write-you-a-vector-db
  A Vector Database Tutorial (over CMU-DB's BusTub system)
  ☆742Updated last year
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,995Updated last week
• anthropics / original_performance_takehome
  Anthropic's original performance take-home, now open for you to try!
  ☆2,313Updated this week
• NVIDIA / cutile-python
  cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
  ☆1,851Updated this week