Static suckless single batch CUDA-only qwen3-0.6B mini inference engine
☆559Sep 8, 2025Updated last year
Alternatives and similar repositories for qwen600
Users that are interested in qwen600 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O☆604Sep 13, 2025Updated last year
- Local Qwen3 LLM inference. One easy-to-understand file of C source with no dependencies.☆214Jul 5, 2025Updated last year
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,086Updated this week
- Nano vLLM☆15,924Apr 26, 2026Updated 5 months ago
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆4,773Sep 27, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Auto Thinking Mode switch for Qwen3 in Open webui☆70May 8, 2025Updated last year
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆45Oct 5, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆6,672Updated this week
- Examples of CUDA implementations by Cutlass CuTe☆283Jul 1, 2025Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆534Jan 20, 2026Updated 8 months ago
- Sparse & quantized LLM training/inference/CPT/SFT/DPO☆28Sep 13, 2026Updated last month
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,323May 17, 2026Updated 5 months ago
- Kernel Library for Large Headdim Attention (64~1024, BF16/FP8/FP4), 1.5x~15x↑ vs PyTorch SDPA.☆340Updated this week
- An AI-powered interface for exploring and understanding arXiv research papers☆245May 12, 2026Updated 5 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- A minimal PyTorch re-implementation of Qwen 3.8☆453Aug 30, 2026Updated last month
- Bub it. Build it. A tiny agent runtime, composable with plugins.☆1,686Updated this week
- Sample Codes using NVSHMEM on Multi-GPU☆30Jan 22, 2023Updated 3 years ago
- GPU documentation for humans☆750Sep 4, 2026Updated last month
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆102May 14, 2026Updated 5 months ago
- Flash Attention from Scratch on CUDA Ampere☆201Sep 1, 2025Updated last year
- Realtime Audio SDK for the Web — audio capture, echo cancellation (AEC), voice activity detection (VAD), and real-time encoding (Opus/PCM…☆123Dec 6, 2025Updated 10 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆158May 10, 2025Updated last year
- ☆14Nov 3, 2025Updated 11 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.☆24Apr 3, 2026Updated 6 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated 3 months ago
- ☆50Jun 3, 2026Updated 4 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆242Jan 14, 2026Updated 9 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,325Aug 26, 2025Updated last year
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆555Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- how to optimize some algorithm in cuda.☆3,317Updated this week
- An end-to-end voice assistant running entirely on Apple Silicon.☆63Nov 29, 2025Updated 10 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆83Aug 12, 2024Updated 2 years ago
- CPU inference for the DeepSeek family of large language models in C++☆325Oct 2, 2025Updated last year
- Fastest kernels written from scratch☆629Aug 15, 2026Updated 2 months ago
- ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs☆17Oct 24, 2025Updated 11 months ago
- 🎉My Collections of CUDA Kernels~☆11Jun 25, 2024Updated 2 years ago