DeepSeek V4 Flash 284B on AMD Strix Halo (gfx1151) — up to 32 tok/s decode & ~250 tok/s prefill via ROCmFPX, DSpark & ROCm 7.2
☆21Aug 28, 2026Updated 2 months ago
Alternatives and similar repositories for ds4fa
Users that are interested in ds4fa are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepSeek-V4-Flash inference for AMD Strix Halo☆28Sep 11, 2026Updated 2 months ago
- High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), …☆95Sep 24, 2026Updated last month
- Winning Qwen and DeepSeek setups for AMD Strix Halo: pinned Ansible recipes and matched benchmarks on a 128 GiB Ryzen AI Max+ 395 / Radeo…☆29Updated this week
- ☆11Feb 11, 2015Updated 11 years ago
- ☆66Jul 27, 2026Updated 3 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Program verification with F* course materials☆12Jul 6, 2019Updated 7 years ago
- OCaml bindings to the number theory library PARI/GP☆12Jan 11, 2025Updated last year
- Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, N…☆235Updated this week
- A minimal, certified, executable HTTP server written in Coq☆11Mar 30, 2021Updated 5 years ago
- A Deepseek V4 Flash 0731 / Vision Exp VLLM stack☆27Sep 24, 2026Updated last month
- A PBT framework☆10Jul 19, 2025Updated last year
- R1CS to Plonk transpiler☆11Jun 12, 2025Updated last year
- Proof-of-concept code for beating Google's ZK proof of quantum cryptanalysis☆16Apr 17, 2026Updated 6 months ago
- Cloud Foundry OpenStack Swift Service☆10Mar 10, 2014Updated 12 years 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.
- Qwen 3.8 27B on a $1,400 Strix Halo: frozen optimal config, 262k needle-exact retrieval, vision fixed, delegation-card certified☆14Updated this week
- 🐺 Simple STARK verifier in cameligo☆11Jun 5, 2023Updated 3 years ago
- Soft debugger client for Unity☆12Feb 1, 2011Updated 15 years ago
- The Quaspy library for Python for simulating and post-processing various quantum algorithms, including Shor's algorithms and Ekerå–Håstad…☆13May 2, 2026Updated 6 months ago
- ☆10Aug 29, 2018Updated 8 years ago
- INTMAX2 is a stateless Layer 2 protocol on Ethereum, combining privacy, speed, and true self-custody.☆12Jan 21, 2026Updated 9 months ago
- The most advanced multisig bitcoin wallet optimized for collaboration.☆12Jun 11, 2026Updated 5 months ago
- ☆12Feb 20, 2026Updated 8 months ago
- Service Discovery for CloudFoundry☆12May 2, 2019Updated 7 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- OCaml bindings for OpenAI API☆19Feb 9, 2024Updated 2 years ago
- The OCaml coding agent☆13Aug 30, 2026Updated 2 months ago
- Finite Fields and Curves in Lean☆14Apr 6, 2023Updated 3 years ago
- ☆11Sep 17, 2013Updated 13 years ago
- Calculus of Constructions Implementation☆17Dec 20, 2019Updated 6 years ago
- Simple modal text editor in Elm☆11May 21, 2015Updated 11 years ago
- Synthesis of Formally Verified Cryptographic Primitives☆18Updated this week
- We combat sloppy arguments in competitive programming and raise the standard of rigor☆31Updated this week
- Serve your models fast on your own infra in 3 steps.☆52Updated 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.
- SSO for services that use CA-based authentication.☆10Jun 27, 2022Updated 4 years ago
- LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context☆100Updated this week
- Midnight trusted setup for PLONK over BLS12-381 repository☆11Mar 17, 2026Updated 7 months ago
- Proving shortest paths with recursive SNARKs☆15Mar 9, 2023Updated 3 years ago
- ☆15Oct 19, 2024Updated 2 years ago
- Docker Broker is an Open Service Broker API-compatible system that provisions Docker-based services on demand☆12Apr 27, 2018Updated 8 years ago
- scan bosh deployments for deployment security issues☆12Aug 16, 2019Updated 7 years ago
Are these results useful?