Qwen3.8-Flash-Next on 4x RTX 3090: vLLM recipe, FP8 QSA KV reader for Ampere, benchmark receipts
☆13Aug 30, 2026Updated 2 months ago
Alternatives and similar repositories for qwen38-flash-next-vllm-3090-recipe
Users that are interested in qwen38-flash-next-vllm-3090-recipe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen3.8 Flash Next AWQ INT4 4x3090 v1: 262K, Vision, FP8 QSA KV and CUDA Graphs on 4x RTX 3090☆16Aug 30, 2026Updated 2 months ago
- Raw speed benchmark traces: Qwen3.8-27B on 4x RTX 3090. llama.cpp GGUF sweeps + 288-point vLLM vs SGLang, NVFP4 vs FP8 matrix.☆14Sep 28, 2026Updated last month
- Idle Kingdoms Route Editor☆10May 21, 2018Updated 8 years ago
- Block-FP8 (W8A16) on NVIDIA V100 / Volta (sm_70) for vLLM — the FP8 path upstream drops on Volta, tuned for sparse MoE.☆15Jul 10, 2026Updated 4 months ago
- vLLM fork for Tesla V100☆15May 31, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- What I run on my inference server: Qwen3.8-Flash-Next on two RTX 3090s, and how I got here☆18Oct 12, 2026Updated last month
- Magisk module to unlock 100/110/120/144/165/180Hz on the Meta Quest Pro (seacliff)☆19Sep 29, 2026Updated last month
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆25Jul 10, 2026Updated 4 months ago
- Script to change between Wacom and Huion drivers☆20Feb 3, 2026Updated 9 months ago
- Library to parse face tracking data from Pico headsets☆16Jun 15, 2023Updated 3 years ago
- Academic presentation template in Typst for researchers☆12Nov 4, 2024Updated 2 years ago
- A little project to convert Java Jar files into MacOS applications☆11Jun 29, 2017Updated 9 years ago
- P2P support for nvidia consumer cards☆27Nov 10, 2026Updated last week
- VR eye-tracking to VRCFaceTracking bridge for hotmirror-based VR headsets (Pimax Crystal/Super, StarVR One, Varjo).☆32Nov 5, 2026Updated 2 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Teach GLM-5.2 to see art: minimal frozen-backbone vision-projector training (method by Harry Partridge)☆14Jul 18, 2026Updated 4 months ago
- Hacker is a Zola theme☆17Aug 29, 2026Updated 2 months ago
- llama-cpp support turboquant and gemma 4☆20May 19, 2026Updated 6 months ago
- Tiron multi-speaker meeting ASR — inference harness☆16Jul 23, 2026Updated 3 months ago
- Voluntary agent-driven context compaction suite for Pi harness.☆13Updated this week
- Write GMail filters and output to importable XML☆13Mar 31, 2016Updated 10 years ago
- My kubernetes cluster configs for nixos☆15Nov 5, 2026Updated 2 weeks ago
- A stupid module that lets you use `dictproxy` on any Python.☆15Aug 6, 2013Updated 13 years ago
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆29Jul 8, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Android read and write serial port, simple implementation with examples.☆11Aug 8, 2026Updated 3 months ago
- Orange Pi 6 Plus GPU bring-up on mainline/Armbian (SCMI ACPI/SMC, resets, Panthor)☆19Oct 30, 2026Updated 3 weeks ago
- AndroGaming.com Carmageddon Android Port, native ARM64 Dethrace-based engine, touch/controller support, graphics improvements and full AI…☆12Oct 28, 2026Updated 3 weeks ago
- A tiny but powerful web framework built on top of lit-html and rxjs☆11Apr 29, 2023Updated 3 years ago
- Ameoba Single key PCB variant designed for simplicity☆14Apr 17, 2023Updated 3 years ago
- C++ version of pyannote audio overlapped speech detection pipeline☆13Feb 14, 2024Updated 2 years ago
- Turn an unrooted Android 11+ phone into a single-line cellular <-> SIP gateway. The phone registers to your PBX (Asterisk / FreePBX / Iss…☆40Nov 8, 2026Updated last week
- ☆13Nov 19, 2023Updated 3 years ago
- LLM Combinator exports real-time results of multi-modal Ollama executions with input from Frigate cameras and HA sensors into HomeAssista…☆14Nov 10, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- marlin_v100 是一个从 vLLM 主树中提取出来的最小 Marlin 独立开发工作区,聚焦于 Marlin dense 与 Marlin MoE 的源码开发、最小构建和轻量验证。它保留了核心 CUDA/C++ 实现、最小 Python 薄封装、生成器测试与主树回写…☆27Jul 2, 2026Updated 4 months ago
- VR Base Stations Manager for HMD☆27Nov 10, 2026Updated last week
- Randomizer for Quest for Glory 1 EGA☆16Nov 12, 2023Updated 3 years ago
- vLLM fork for Tesla V100 (SM70) — extends 1CatAI's AWQ support and adds GGUF support☆27Jun 20, 2026Updated 5 months ago
- Constructive Solid Geometry (CSG) and Quick Hull Library for golang☆10Oct 30, 2019Updated 7 years ago
- Legacy version of https://github.com/LedgerHQ/app-cardano☆12Sep 1, 2026Updated 2 months ago
- EaglercraftX replit archive☆27Mar 2, 2023Updated 3 years ago
Are these results useful?