DeepSeek-V4.1-Flash-1017 on 8x V100-SXM2 (2018): 119.0 tok/s decode, 120.8 thinking on (measured), 524K context, 300K-token first token in 178 s. PP2xTP4 port of 1Cat-vLLM #1277 with every patch, measurement and lost lever. PLI Labs.
☆30Nov 11, 2026Updated this week
Alternatives and similar repositories for Volta-sPLIt-DeepSeek-V4.1-Flash-1017-8xV100-SXM2-PP2xTP4
Users that are interested in Volta-sPLIt-DeepSeek-V4.1-Flash-1017-8xV100-SXM2-PP2xTP4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Universal Offer Hub: one Chrome extension for Chase, Amex, Capital One, and more☆15Nov 2, 2026Updated last week
- LLM inference in C/C++☆43Nov 5, 2026Updated last week
- GridCartographer Mapping work☆10May 5, 2024Updated 2 years ago
- A Spotify player with a Firebase interface☆14Jun 6, 2016Updated 10 years ago
- JS82MS calculator with esp32 s3☆16Oct 11, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Notes and documentation on reverse engineering the SteelSeries Arctis Nova Pro Wireless USB Protocol☆12May 14, 2023Updated 3 years ago
- GPU peer-to-peer over dynamic BAR1 for GeForce cards: patched NVIDIA open kernel modules.☆22Nov 6, 2026Updated last week
- Lightweight voice companion for Home Assistant on old smart displays: on-device wake word and reflexes, an animated character, AirPlay mu…☆20Updated this week
- git clone of http://code.google.com/p/axi-bfm/☆18May 21, 2013Updated 13 years ago
- Run a large local model across heterogeneous computers using neuron-sliced experts.☆25Nov 6, 2026Updated last week
- A set of cog recipes for C++ reflection☆15Aug 21, 2011Updated 15 years ago
- A custom MOTD for Ubuntu.☆14Sep 21, 2024Updated 2 years ago
- Ceph, rewritten from scratch in Rust: wire-compatible daemons and client libraries for a huge leap in performance and stability. OSD with…☆49Updated this week
- Ultra-light Debian 13 for the Lenovo ThinkSmart View (CD-18781Y): ~190 MB of RAM, GPU, speaker, microphones, Wi-Fi, sensors☆26Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- My fork of the Sick Lidar Toolbox for C++ and Matlab☆14May 10, 2016Updated 10 years ago
- Course work from MIT's "Introduction to Computer Science and Programming Using Python" on edX.☆13Aug 1, 2017Updated 9 years ago
- Find (missing) dependencies in R-source code☆13Oct 1, 2025Updated last year
- AI SRE agent diagnosing Kubernetes incidents over Google Chat — security-first sandbox: NixOS VM, default-deny egress, hard tool denylist…☆15Oct 6, 2026Updated last month
- Give GeForce cards (Turing and later) a BAR1 at least as large as their VRAM on Linux, without flashing.☆23Nov 6, 2026Updated last week
- SOINN implementation with C++☆17Nov 29, 2012Updated 13 years ago
- Give a friend a quota-capped corner of your ZFS pool for raw encrypted backups, without giving them a shell☆21Oct 3, 2026Updated last month
- The StreamDeck vJoy Controller Plugin is a powerful tool that transforms your StreamDeck into a flexible vJoy controller. This plugin all…☆22Aug 12, 2026Updated 3 months ago
- ☆17Jan 12, 2025Updated last year
- 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.
- Mirror of ocitysmap repository at savannah.nongnu.org☆22Feb 1, 2017Updated 9 years ago
- ☆16Updated this week
- REST API for Keyper SSH Key Based Authentication Manager.☆20May 7, 2021Updated 5 years ago
- Implementation of MOSSE filters with SVM classification for driver in-car head orientation☆16Jan 23, 2013Updated 13 years ago
- Example projects for snickerdoodle☆29Jan 23, 2026Updated 9 months ago
- A Debian repository synchronization daemon☆19Dec 20, 2025Updated 10 months ago
- Python library for interfacing with Rigol DS1000Z series oscilloscopes.☆30Oct 17, 2026Updated 3 weeks ago
- Angular frontend for 3D Print Log — a web app for tracking 3D prints, printers, filaments, and print costs.☆14Updated this week
- 3D Graphics Engine for Real-Time Applications. Written in C++ and OpenGL☆19Nov 1, 2015Updated 11 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Color targets from vendors for color calibration☆23Aug 19, 2016Updated 10 years ago
- code generator, currently only targeting spidermonkey☆23Apr 4, 2013Updated 13 years ago
- a Micropython driver for the SBUS protocol☆28Jul 17, 2016Updated 10 years ago
- Uberblok: an interactive museum of ZFS internals☆27Nov 1, 2026Updated last week
- Skills for AIs to do evals, error analysis, and more.☆12Feb 19, 2026Updated 8 months ago
- Collaborative peer-to-peer 3D prototyping in the browser — Svelte 5, three.js, WebXR, node-graph behaviour and physics. No backend.☆37Updated this week
- An easy way to copy your music off old iPods.☆23Apr 11, 2026Updated 7 months ago
Are these results useful?