A single-file educational implementation for understanding vLLM's core concepts and running LLM inference.
☆45Apr 7, 2026Updated 3 months ago
Alternatives and similar repositories for cleanvllm
Users that are interested in cleanvllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Nano vLLM☆25Aug 11, 2025Updated 11 months ago
- RLVR training for LLM in CUDA/C++☆42Updated this week
- LLM training parallelisms (DP, FSDP, TP, PP) in pure C☆29Jan 27, 2026Updated 6 months ago
- Implement some method of LLM KV Cache Sparsity☆41Jun 6, 2024Updated 2 years ago
- A light llama-like llm inference framework based on the triton kernel.☆188Jan 5, 2026Updated 6 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Super fast serving stack for LLM on Windows/Linux/Macos☆17Dec 17, 2025Updated 7 months ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆211Mar 18, 2026Updated 4 months ago
- This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference sp…☆69Apr 24, 2026Updated 3 months ago
- ☆106Sep 9, 2024Updated last year
- ☆13Jun 16, 2024Updated 2 years ago
- ☆11Mar 9, 2022Updated 4 years ago
- ☆19Apr 15, 2025Updated last year
- [IPDPS 2024] Adaptive neighbor sampling for temporal GNN☆16Feb 17, 2025Updated last year
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆241Jan 14, 2026Updated 6 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆356Nov 2, 2025Updated 8 months ago
- 用pytorch训练18层残差神经网络，用pyqt设计界面☆12Jun 23, 2020Updated 6 years ago
- Author's PyTorch Implementation of Deep Homomorphic Policy Gradient (DHPG) - NeurIPS 2022 and JMLR 2024☆24Apr 8, 2024Updated 2 years ago
- Single-file truly minimal implementation of state-of-the-art reinforcement learning algorithms.☆21Feb 13, 2023Updated 3 years ago
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆62Nov 8, 2024Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆170Dec 23, 2025Updated 7 months ago
- [ACL 2026 Main] See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video …☆27Jul 4, 2026Updated 3 weeks ago
- FlashSparse significantly reduces the computation redundancy for unstructured sparsity (for SpMM and SDDMM) on Tensor Cores through a Swa…☆39Oct 5, 2025Updated 9 months ago
- 尚观嵌入式课程QT图形界面课程☆11Dec 26, 2016Updated 9 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Nano vLLM v1 engine☆16Aug 6, 2025Updated 11 months ago
- DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing (WACV 2025)☆13Feb 7, 2026Updated 5 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆92Jul 17, 2025Updated last year
- Render RL environments on a web browser with just one extra line of code.☆20Sep 10, 2020Updated 5 years ago
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆16Nov 11, 2024Updated last year
- ☆14Jul 22, 2026Updated last week
- Estimate Your LLM's Token Toll Across Various Platforms and Configurations☆39Nov 9, 2025Updated 8 months ago
- Official implementation of paper "Masked Distillation with Receptive Tokens", ICLR 2023.☆10Mar 13, 2023Updated 3 years ago
- ☆16Mar 13, 2023Updated 3 years 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.
- ☆23Jan 18, 2026Updated 6 months ago
- 中科大郑启龙2021年并行程序设计课程实验☆11Jan 15, 2022Updated 4 years ago
- 📚 LaTeX templates and tools for creating beautiful, structured documents 📝☆14Oct 24, 2025Updated 9 months ago
- Flash Attention from Scratch on CUDA Ampere☆187Sep 1, 2025Updated 10 months ago
- AI Hedge Fund Repo integrate with DeepSeek V3 and R1 hosted on SiliconFlow.☆12Feb 3, 2025Updated last year
- llm deploy project based onnx.☆49Oct 9, 2024Updated last year
- Applying PBT optimization technique to different domains☆10Oct 16, 2019Updated 6 years ago