EXL3 inference engine for Qwen3.8-Flash-Next on AMD Strix Halo: Ryzen AI Max+ 395, Radeon 8060S, gfx1151, ROCm/HIP in C++20. Exact speculative decoding, OpenAI-compatible server, and speed claims stated against measured hardware ceilings.
☆16Nov 2, 2026Updated this week
Alternatives and similar repositories for crucible-strix-halo
Users that are interested in crucible-strix-halo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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☆97Updated this week
- Auto-built Docker image of 1Cat-vLLM for NVIDIA Tesla V100 (sm_70/Volta) with CUDA 12.8 — rebuilt daily when upstream releases☆12Jul 22, 2026Updated 3 months ago
- ☆14Sep 10, 2026Updated last month
- LLM inference in C/C++☆256Updated this week
- A Deepseek V4 Flash 0731 / Vision Exp VLLM stack☆26Sep 24, 2026Updated last month
- 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.
- Stable, high-throughput inference server for multi-GPU NVIDIA V100 (SM70): Qwen3.8 Flash-Next with AWQ / NVFP4, multimodal input, CPU/dis…☆39Updated this week
- LLM inference in C/C++☆43Updated this week
- DeepSeek-V4-Flash inference for AMD Strix Halo☆28Sep 11, 2026Updated last month
- CIRU llama.cpp runtime for Qwen3.8-Flash-CIRU-STRIX-IU4 on AMD Strix Halo☆21Sep 28, 2026Updated last month
- 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…☆229Updated this week
- Fork of llama.cpp Nvida Volta V100 (tensor parallelism 4 x v100 GPU)☆12Updated this week
- HIP kernels for AMD Strix Halo (gfx1151) and a vLLM plugin that runs them on stock upstream vLLM: up to 31x faster prefill and ~2x decode…☆21Updated this week
- NInfer on Tesla V100 (sm_70): Qwen3.8-27B deployment, build/convert scripts, systemd service, and cross-engine benchmark (vs llama.cpp). …☆53Sep 15, 2026Updated last month
- ☆24Jun 27, 2026Updated 4 months 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.
- llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefil…☆71Updated this week
- Third party commentaries for UniqueBible☆13Apr 8, 2021Updated 5 years ago
- 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☆20Aug 28, 2026Updated 2 months ago
- Run local LLMs on a Tesla V100-SXM2-16GB: prebuilt binaries, serve scripts, and setup for Windows and Linux (Qwen3 + Gemma 4, Claude Code…☆20Sep 1, 2026Updated 2 months ago
- Path of Exile Discord bot to quickly fetch data from wiki/poe.ninja☆13Jul 21, 2026Updated 3 months ago
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆86Sep 16, 2026Updated last month
- Ermis: A decentralized, secure and open-source messaging platform for real-time communication.☆45Updated this week
- ☆38Oct 22, 2026Updated 2 weeks ago
- ☆11Feb 11, 2015Updated 11 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.
- The wireless split keyboard firmware using ZMK has been optimized for E-ink screens and the Cirque trackpad.☆19Sep 17, 2026Updated last month
- Various Docker images☆26Oct 20, 2022Updated 4 years ago
- Sisyphe is a modulable NodeJS BIG-DATA analyser & transformer☆12Oct 16, 2023Updated 3 years ago
- Libegpu is a library for enumerating eGPU devices & enclosures.☆16Nov 24, 2025Updated 11 months ago
- Demo of loading sksl shader files as Skia shaders in Expo with Metro☆12Apr 11, 2024Updated 2 years ago
- Firmware that drives the 2nd generation Afridev Sensor☆15May 7, 2021Updated 5 years ago
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆21Oct 16, 2026Updated 3 weeks ago
- Elasticsearch Scroll query results as a Readable Node.js Stream☆10Jun 16, 2024Updated 2 years ago
- Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan p…☆28Aug 17, 2026Updated 2 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Raytracer demo written in Dart☆14Apr 20, 2015Updated 11 years ago
- A Windows Forms .net application for common IT desktop management functions.☆10Sep 26, 2021Updated 5 years ago
- Like XSL/XML but for JSON.☆13Nov 12, 2016Updated 9 years ago
- ComfyUI MiniMax H3 inference optimizations for NVIDIA Tesla V100 (SM70)☆31Sep 29, 2026Updated last month
- Qwen3.8-Flash-Next (W4A16) on 2x CMP 170HX: 110 tok/s decode, 7K prefill, 800 tok/s @ 23 concurrent - runs on 38 GB home RAM, no pinned m…☆20Sep 18, 2026Updated last month
- Build complex lucene query strings with basic functions☆11Oct 26, 2026Updated last week
- CherryPick is a modular, open-source dependency injection ecosystem for Dart and Flutter☆12Updated this week