Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux builds.
☆56Oct 15, 2026Updated this week
Alternatives and similar repositories for ninfer-3090
Users that are interested in ninfer-3090 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆459Updated this week
- ☆46Jul 22, 2026Updated 2 months ago
- The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own …☆106Updated this week
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆18Apr 26, 2026Updated 5 months ago
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆84Oct 10, 2026Updated last week
- 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.
- llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 95+ tok/s over a 100K-token gen…☆182Updated this week
- Code for my collection of predictors/classifiers/etc☆14Jul 18, 2024Updated 2 years ago
- A port of an HMM / speech recognition C library to Android☆12Sep 23, 2016Updated 10 years ago
- ☆39Jul 16, 2026Updated 3 months ago
- Get 99.13% test accuracy MNIST with only 300 lines of code CNN by JAVA☆11Jul 30, 2018Updated 8 years ago
- ROCm/AMD GPU benchmark suite for llama.cpp, whisper.cpp, PyTorch☆21Feb 4, 2026Updated 8 months ago
- ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, ver…☆56Sep 30, 2026Updated 2 weeks 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), …☆90Sep 24, 2026Updated 3 weeks ago
- Install and use compiled privacy-filter.cpp binaries from Laravel applications.☆57Oct 8, 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.
- 基于DNN和DTW算法配合VAD截取的微语音识别框架☆13Sep 27, 2017Updated 9 years ago
- ESP8266 core for Arduino☆15Oct 13, 2016Updated 10 years ago
- 一个轻量级的小程序开发脚手架，基于gulp☆11Aug 14, 2019Updated 7 years ago
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,108Updated this week
- A Rust library for draping polygons over terrain with gfx☆11Mar 5, 2018Updated 8 years ago
- Differential-KV (DKV) is a sparse KV-cache inference runtime designed for high-efficiency, memory-bounded long-context Large Language Mod…☆21Updated this week
- MCP server for Tailscale, backed by the tailscale CLI and control-plane REST API☆14Oct 10, 2026Updated last week
- 设备固件库，适用于IntoRobot系列产品☆19Oct 8, 2018Updated 8 years ago
- osintstalker☆13Oct 23, 2013Updated 12 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Thermal pocket printer - BLE protocol reverse engineering, Python CLI, and web GUI☆24Sep 4, 2026Updated last month
- A Light CNN Framework！☆16Apr 8, 2019Updated 7 years ago
- Batched, checkpointed, resumable data operations for Laravel — backfills, cleanups, and migrations that survive deploys, crashes, and Ctr…☆35Aug 14, 2026Updated 2 months ago
- A project related to never.☆12Dec 18, 2017Updated 8 years ago
- A fast and stealthy credential harvester☆11Aug 14, 2015Updated 11 years ago
- Convert separated character-art layers into a reusable, riggable 2D puppet (nijilive .inp + Live2D .moc3).☆46Sep 7, 2026Updated last month
- A fully procedural Formula 1 racing game in three.js — no asset files, no network fetches. Built by fanned-out agents under the Gauntlet …☆47Aug 2, 2026Updated 2 months ago
- OpenCode plugin: Ralph outer loop + RLM inner loop — iterative AI development with file-first discipline and sub-agent support☆32Jun 30, 2026Updated 3 months ago
- Bash script presents crontab in human readable form.☆11Apr 21, 2018Updated 8 years ago
- 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.
- SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)☆41Sep 17, 2026Updated last month
- Qwen3.8-Flash-Next (MoE, NVFP4) and Qwen3.8-27B on two 16 GB consumer GPUs: two-GPU tensor parallel, experts offloaded to CPU. Formerly n…☆43Updated this week
- 2x DGX Spark (GB10) running DeepSeek-V4-Flash: dual-node FP8 TP=2 (~41 tok/s single / ~350 agg), single-node ds4, a 10-model GGUF benchma…☆30Jun 16, 2026Updated 4 months ago
- Ekbasis: an open world model for agents. What an action will do, before it is done.☆19Updated this week
- Statistically-Lossless Quantization of Large Language Models☆21Oct 8, 2026Updated last week
- Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan p…☆27Aug 17, 2026Updated 2 months ago
- ☆14Jun 8, 2023Updated 3 years ago