skyzh / tiny-llmLinks
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
☆3,356Updated 2 weeks ago
Alternatives and similar repositories for tiny-llm
Users that are interested in tiny-llm are comparing it to the libraries listed below
Sorting:
- My learning notes/codes for ML SYS.☆4,012Updated 3 weeks ago
- Nano vLLM☆7,173Updated last month
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,168Updated this week
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,638Updated 6 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆5,373Updated this week
- ☆1,601Updated 3 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆3,743Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,911Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,952Updated last week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,863Updated 2 months ago
- Supercharge Your LLM with the Fastest KV Cache Layer☆5,671Updated this week
- An ML Systems Onboarding list☆917Updated 9 months ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,928Updated 5 months ago
- Material for gpu-mode lectures☆5,197Updated last month
- Large Language Model (LLM) Systems Paper List☆1,563Updated last week
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆8,207Updated last week
- NanoGPT (124M) in 3 minutes☆3,694Updated last week
- Democratizing Reinforcement Learning for LLMs☆4,600Updated this week
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆1,884Updated last week
- A lightweight data processing framework built on DuckDB and 3FS.☆4,813Updated 7 months ago
- Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.☆609Updated 8 months ago
- slime is an LLM post-training framework for RL Scaling.☆2,232Updated this week
- Tile primitives for speedy kernels☆2,838Updated last week
- Fast, Flexible and Portable Structured Generation☆1,323Updated last week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,944Updated 6 months ago
- Textbook on reinforcement learning from human feedback☆1,279Updated this week
- Renderer for the harmony response format to be used with gpt-oss☆3,926Updated 2 months ago
- Puzzles for learning Triton☆2,074Updated 11 months ago
- Artificial Neural Engine Machine Learning Library☆1,216Updated last month
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,421Updated this week