This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed.
☆75Apr 24, 2026Updated 5 months ago
Alternatives and similar repositories for nano-kvllm
Users that are interested in nano-kvllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A sparse-first inference engine (SparseEngine).☆99Updated this week
- RLVR training for LLM in CUDA/C++☆42Jul 25, 2026Updated 2 months ago
- 分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等☆4,185Sep 20, 2026Updated 3 weeks ago
- A single-file educational implementation for understanding vLLM's core concepts and running LLM inference.☆47Apr 7, 2026Updated 6 months ago
- 基于Rust的大模型推理框架☆13Oct 3, 2026Updated 2 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Super fast serving stack for LLM on Windows/Linux/Macos☆17Updated this week
- ☆26Apr 2, 2026Updated 6 months ago
- Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation☆1,074Aug 29, 2026Updated last month
- A from-scratch Prefill/Decode disaggregation inference engine for LLMs☆161May 10, 2026Updated 5 months ago
- The training framework of PCMind-2.1-Kaiyuan-2B built on MindFormers☆15Dec 9, 2025Updated 10 months ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆223Mar 18, 2026Updated 6 months ago
- ☆14Oct 11, 2023Updated 3 years ago
- ☆21May 11, 2026Updated 5 months ago
- Nano vLLM☆15,870Apr 26, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.☆21May 20, 2026Updated 4 months ago
- Analyze LLM inference: FLOPs, memory, Roofline model. Supports GQA, MoE, MLA, RoPE, SwiGLU. 19 models × 20+ hardware platforms.☆22Apr 16, 2026Updated 6 months ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- ☆46Oct 11, 2025Updated last year
- ☆19Mar 29, 2026Updated 6 months ago
- The ResNet18 and RepVGG model was used for 72 metal oxide gas sensor datasets for 10 gases.☆12Apr 5, 2024Updated 2 years ago
- [ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading☆26Jan 6, 2026Updated 9 months ago
- 高性能短序列稀疏Mask Attention CUDA算子，针对<1K序列+75%稀疏度优化☆79Mar 18, 2026Updated 6 months ago
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,082Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆23Aug 20, 2025Updated last year
- An example Hardware Processing Engine☆12Feb 4, 2023Updated 3 years ago
- A simple environment for writing and experimenting with hand-written CUDA PTX kernels.☆19Sep 11, 2025Updated last year
- This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.☆608Mar 1, 2026Updated 7 months ago
- Website about the project WorkflowHub☆14Aug 21, 2026Updated last month
- 注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能☆210Aug 11, 2025Updated last year
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆25Oct 5, 2024Updated 2 years ago
- fake CUTLASS to get peformance☆26Apr 28, 2026Updated 5 months ago
- ☆21Aug 19, 2024Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Implementation from scratch in CUDA C++ of image processing algorithms.☆26Oct 26, 2020Updated 5 years ago
- Neuromorphic ASIC with 96 neurons on Tiny Tapeout 7☆11May 25, 2024Updated 2 years ago
- [ICML2025] KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference☆32Jan 27, 2026Updated 8 months ago
- ☆13Jun 1, 2022Updated 4 years ago
- ☆14Oct 22, 2023Updated 2 years ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆23Mar 15, 2024Updated 2 years ago
- Implementation of the logging layer of our SOSP '23 paper Halfmoon☆11Jul 28, 2023Updated 3 years ago