Single-stream LLM inference engine for Qwen3.8-27B on one RTX 5090 — int4 quantization + speculative decoding + custom Triton/CUDA kernels; 229–379 tok/s vs llama.cpp/SGLang/vLLM at batch size 1.
☆25Sep 12, 2026Updated 2 months ago
Alternatives and similar repositories for token-rush
Users that are interested in token-rush are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implement all of the components (tokenizer, model architecture, optimizer) necessary to train a standard BPE-encoder Transformer language…☆12Sep 21, 2025Updated last year
- Reasoning LLMs optimized for Chisel code generation☆26Jun 19, 2025Updated last year
- ☆19Aug 17, 2026Updated 3 months ago
- Occamy is a preemptive buffer management for on-chip shared-memory switches☆13Feb 28, 2026Updated 8 months ago
- Source code for CRouting☆12Sep 10, 2025Updated last year
- 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.
- SJTU AI1101(原AI001) 大作业-基于python和yolov5实现的简单FPS类辅助瞄准☆127Feb 22, 2023Updated 3 years ago
- ☆12May 10, 2024Updated 2 years ago
- A gallery of Boar :)☆41Aug 10, 2026Updated 3 months ago
- Application Layer DDoS attack detection using fast entropy computation method☆13May 18, 2024Updated 2 years ago
- UCSD ECE277 GPU Programming coursework: GPU-accelerated reinforcement learning on CUDA C with Nsight System☆14Aug 17, 2021Updated 5 years ago
- Parser utility to generate ASTs from PHP source code suitable to be processed by Joern.☆15Jan 27, 2019Updated 7 years ago
- ☆13Jan 23, 2021Updated 5 years ago
- A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking☆14Feb 18, 2026Updated 8 months ago
- PyTorch implementation of Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion☆14Jun 5, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Description: Experimental nano-vLLM fork for Qwen3.6 support, CUDA Graph, paged KV cache, and inference-engine learning.☆22Oct 15, 2026Updated last month
- ☆13Sep 28, 2025Updated last year
- SJMC 社团迎新 / 介绍页(首次使用于 2024 上海交通大学录取通知书)☆10Nov 30, 2024Updated last year
- Flow level simulation☆17Nov 22, 2015Updated 10 years ago
- ☆14Mar 26, 2025Updated last year
- ☆21Jun 16, 2026Updated 5 months ago
- Course Notes of Shanghai Jiao Tong University☆12Feb 27, 2022Updated 4 years ago
- 中山大学电子与信息工程学院25年春,通信工程的工程应用训练课项目——智能便携式电子负载☆16Feb 8, 2026Updated 9 months ago
- ☆17May 8, 2021Updated 5 years 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.
- pythonFlask+音视频SDK+OpenVino+OpenPose实现网课场景坐姿检测☆16Mar 20, 2023Updated 3 years ago
- 根据上海交通大学研究生院给出的研究生学位论文写作模版(https://www.gs.sjtu.edu.cn/info/1136/8374.htm) 进行修改适配,解决latex模版中的一些错误,以及和word模版不一致问题☆39Jan 4, 2023Updated 3 years ago
- [TMLR 26]: "UniRec: Unified Multimodal Encoding for LLM-Based Recommendations", Zijie Lei, Tao Feng, Zhigang Hua, Yan Xie, Guanyu Lin, Sh…☆15Jul 9, 2026Updated 4 months ago
- Low level algorithms for persistent memory.☆16Feb 9, 2021Updated 5 years ago
- Artifact Evaluation for OSDI'26 paper CoPilotIO: CPU as a Co-pilot for GPU I/O to Free GPU Compute☆29May 9, 2026Updated 6 months ago
- vscode-drawio增强版,提供代码跳转功能☆10Feb 20, 2025Updated last year
- Documentation for the Radar Chart Widget (Unreal Engine) Plugin☆20Jan 18, 2021Updated 5 years ago
- ☆21Jul 15, 2025Updated last year
- 一个由 Python 编写的轻量级、可扩展的QQ机器人前端☆71Jan 16, 2026Updated 10 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Profiling and Improving the PyTorch Dataloader for high-latency Storage☆21Apr 18, 2023Updated 3 years ago
- 我们在TAAC2026初赛的最高的分代码,测试AUC:0.831174☆15May 25, 2026Updated 5 months ago
- Code Scorer using LLM☆12Jun 22, 2026Updated 4 months ago
- 中山大学体育场馆管理与预定系统助手☆26Apr 9, 2021Updated 5 years ago
- Run a Tauri-like application without installation.☆15Mar 2, 2024Updated 2 years ago
- Python Scritpt which can be embedded into PyTorch model to print the model size.☆19Apr 19, 2021Updated 5 years ago
- [AAAI 2025] Official Implementation of "HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting"☆19Feb 17, 2025Updated last year
Are these results useful?