My learning notes for ML SYS.
β5,444Jan 30, 2026Updated last month
Alternatives and similar repositories for Awesome-ML-SYS-Tutorial
Users that are interested in Awesome-ML-SYS-Tutorial are comparing it to the libraries listed below
Sorting:
- verl: Volcano Engine Reinforcement Learning for LLMsβ19,519Updated this week
- πLeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginnersπ, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.πβ9,755Feb 25, 2026Updated last week
- FlashInfer: Kernel Library for LLM Servingβ5,057Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.β23,905Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.β4,843Updated this week
- πA curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.πβ5,040Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)β9,084Updated this week
- slime is an LLM post-training framework for RL Scaling.β4,536Updated this week
- Materials for learning SGLangβ766Jan 5, 2026Updated 2 months ago
- how to optimize some algorithm in cuda.β2,841Updated this week
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.β3,586Updated this week
- Material for gpu-mode lecturesβ5,800Feb 1, 2026Updated last month
- Distributed Compiler based on Triton for Parallel Systemsβ1,371Feb 13, 2026Updated 3 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernelsβ5,284Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabiliβ¦β3,919Updated this week
- The repository has collected a batch of noteworthy MLSys bloggers (Algorithms/Systems)β324Jan 5, 2025Updated last year
- π Awesome System for Machine Learning β‘οΈ AI System Papers and Industry Practice. β‘οΈ System for Machine Learning, LLM (Large Language Modβ¦β3,728Jul 25, 2025Updated 7 months ago
- Ongoing research training transformer models at scaleβ15,461Updated this week
- Nano vLLMβ11,920Nov 3, 2025Updated 4 months ago
- Efficient Triton Kernels for LLM Trainingβ6,162Feb 27, 2026Updated last week
- Official Repo for Open-Reasoner-Zeroβ2,087Jun 2, 2025Updated 9 months ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovationβ7,970May 15, 2025Updated 9 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMsβ71,883Updated this week
- Puzzles for learning Triton, play it with minimal environment configuration!β634Dec 28, 2025Updated 2 months ago
- Fast and memory-efficient exact attentionβ22,460Updated this week
- π Efficient implementations of state-of-the-art linear attention modelsβ4,474Updated this week
- Large Language Model (LLM) Systems Paper Listβ1,849Feb 27, 2026Updated last week
- FlashMLA: Efficient Multi-head Latent Attention Kernelsβ12,505Feb 6, 2026Updated last month
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.β1,264Aug 28, 2025Updated 6 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.β3,585Feb 26, 2026Updated last week
- Simple RL training for reasoningβ3,830Dec 23, 2025Updated 2 months ago
- Disaggregated serving system for Large Language Models (LLMs).β778Apr 6, 2025Updated 11 months ago
- DeepEP: an efficient expert-parallel communication libraryβ9,005Feb 9, 2026Updated 3 weeks ago
- A throughput-oriented high-performance serving framework for LLMsβ947Oct 29, 2025Updated 4 months ago
- A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 π and reasoning techniques.β6,896Dec 17, 2025Updated 2 months ago
- Reproduce R1 Zero on Logic Puzzleβ2,439Mar 20, 2025Updated 11 months ago
- A Datacenter Scale Distributed Inference Serving Frameworkβ6,154Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scalingβ6,206Feb 27, 2026Updated last week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizatβ¦β12,993Updated this week