Reproducible Qwen3.8-27B GPTQ INT4 + MTP4 inference on Intel Arc Pro B70 using vLLM XPU — 84.65 tok/s median.
☆47Sep 9, 2026Updated last month
Alternatives and similar repositories for intel-arc-pro-b70-qwen38-vllm
Users that are interested in intel-arc-pro-b70-qwen38-vllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible AP…☆19Updated this week
- EXL3 (exllamav3 trellis) inference on Intel Arc Battlemage: bit-exact ESIMD kernels as a vLLM XPU plugin☆38Sep 26, 2026Updated last month
- ☆75Updated this week
- Qwen3.8-27B EXL3 + DFlash2 speculative decoding on an AMD RX 7900 XTX (exllamav3-rocm): recipe, patches, benchmarks☆21Updated this week
- Qwen3.8-Flash-Next (125B MoE) on a 8GB+ Multi Vendor GPU 🥳No CUDA！☆321Oct 30, 2026Updated last 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.
- ☆46Updated this week
- ☆589Updated this week
- Intel Arc LLM inference server (A770/B60): Qwen hybrids up to Qwen3.8-Flash-Next (512-expert MoE through an expert cache in VRAM and host…☆26Updated this week
- ☆16Oct 20, 2026Updated 2 weeks ago
- Find AI/LLM security vulnerabilities in your code before attackers do — covers prompt injection, MCP tool poisoning, RAG data poisoning, …☆25Updated this week
- Universal Windows Driver information for ITPros and UHFT (UWD HSA Fix Tool).☆13Apr 26, 2021Updated 5 years ago
- Fish-shell package for Unraid (Slackware)☆10Sep 10, 2026Updated last month
- Makes Intel Arc Pro B70 GPUs actually fast on Ubuntu Server. 11 llama.cpp cherry-picks that fix the big B70 bugs (MoE slot-init SEGV, Q8_…☆28May 10, 2026Updated 5 months ago
- Misc scripts☆13Jan 14, 2020Updated 6 years ago
- 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.
- Uncompress and compress sqlite db from Hogwarts Legacy gvas save file☆11Jun 9, 2024Updated 2 years ago
- Windows GUI for building better Kokoro TTS voice outputs. Combines Kokoro voice random-walk search, target-audio scoring, RVC model train…☆14Aug 22, 2026Updated 2 months ago
- copyparty with patent-restricted features added back in☆14Oct 15, 2026Updated 3 weeks ago
- A calm, room-by-room dashboard for Home Assistant, with its own Studio.☆18Updated this week
- Custom Import Script for Sonarr/Radarr/Lidarr to reset the mod-time of imported files.☆14Aug 29, 2026Updated 2 months ago
- ☆12Oct 28, 2019Updated 7 years ago
- Age of AI — a browser-based multiplayer RTS inspired by Age of Empires. Open source, made with AI. Playable in English, Portuguese & Span…☆24Jul 28, 2026Updated 3 months ago
- Build and benchmark notes for houston, a local LLM inference server with four Tesla P100 16GB cards (64GB VRAM): hardware, BIOS fix, llam…☆23Oct 22, 2026Updated 2 weeks ago
- 🕵️♂️ Advanced phone number OSINT suite engineered for silent reconnaissance. Extracts masked emails, profile avatars and uncovers cros…☆41Sep 30, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Frame-accurate seeking for IINA☆15Feb 23, 2026Updated 8 months ago
- An open source multi-function instrument for everyone☆21Oct 16, 2026Updated 3 weeks ago
- A tool to do a "touch" over the nzb to mark an article downloaded☆12Sep 6, 2026Updated 2 months ago
- Cleanup and settings for any windows☆12Updated this week
- A comprehensive GUI wrapper application for Apple's Foundation Models Adapter Training Toolkit, providing an intuitive interface for trai…☆19Jun 10, 2026Updated 4 months ago
- Autonomous, local-first multi-agent AutoML platform. Zero cloud costs, zero API keys, 100% private. Benchmarks 7 algorithms, tunes hyperp…☆23Oct 26, 2026Updated last week
- Library for using Twitter API with Arduino-ESP32☆18May 5, 2018Updated 8 years ago
- Repo for holding ffmpeg build scripts that produce standalone ffmpeg build with all codecs included☆10May 22, 2020Updated 6 years ago
- v2 of the nzbX indexing engine, being developed from scratch.☆12Jul 10, 2013Updated 13 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆14Sep 24, 2024Updated 2 years ago
- android☆10Mar 4, 2015Updated 11 years ago
- ☆12Aug 7, 2026Updated 2 months ago
- ☆15Jan 25, 2021Updated 5 years ago
- ☆14Apr 7, 2023Updated 3 years ago
- correlate an SPI capture of an AMD boot procedure to the PSP firmware components☆17Jan 13, 2026Updated 9 months ago
- An open-source AI assisted firmware analysis tool☆16Mar 5, 2026Updated 8 months ago