Multi-GPU prefill acceleration for llama.cpp
☆15Oct 23, 2026Updated this week
Alternatives and similar repositories for TurboPrefill
Users that are interested in TurboPrefill are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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 6 months ago
- Коллекция промтов для комфорной работы с Cursor☆19Jan 21, 2026Updated 9 months ago
- Unlocking NVIDIA CMP 90HX (GA102): kernel 6.12☆43Aug 22, 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.☆13Sep 28, 2026Updated last month
- Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix H…☆36Updated this week
- 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.
- Qwen3.8-Flash-Next at full 262k context on 8 GB RAM and 16 GB VRAM—20 tok/s generation and 1,600 tok/s prefill.☆48Updated this week
- A little project to convert Java Jar files into MacOS applications☆11Jun 29, 2017Updated 9 years ago
- HikVision IP Camera Alarm Server to MQTT☆14Sep 20, 2023Updated 3 years ago
- Rex library for text generation and manipulation☆21May 18, 2026Updated 5 months ago
- Proxima lets existing GPUs serve 4x more concurrent requests☆26Aug 19, 2026Updated 2 months ago
- Qwen3.8-Flash-Next (MoE) and Qwen3.8-27B on one or two 16 GB RTX 50-series GPUs: experts offloaded to CPU, two-GPU tensor parallel. 64 GB…☆89Updated this week
- Local LLM speed measurements from a 4x RTX 3090 rig, with exact launch commands and per-run provenance.☆18Aug 15, 2026Updated 2 months ago
- A high-throughput LLM serving engine with non-uniform KV cache compression, built on vLLM☆16Sep 9, 2026Updated last month
- Ameoba Single key PCB variant designed for simplicity☆13Apr 17, 2023Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Orange Pi 6 Plus GPU bring-up on mainline/Armbian (SCMI ACPI/SMC, resets, Panthor)☆17Feb 13, 2026Updated 8 months 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 last year
- Custom HIP inference engine for AMD MI50/MI60 (gfx906)☆18Oct 4, 2026Updated 3 weeks ago
- What I run on my inference server: Qwen3.8-Flash-Next on two RTX 3090s, and how I got here☆17Oct 12, 2026Updated 2 weeks ago
- MCP for TimesFM-3: univariate or joint multivariate forecasts with q10–q90 and optional covariates. Weights are non-commercial.☆16Sep 2, 2026Updated last month
- Android read and write serial port, simple implementation with examples.☆11Aug 8, 2026Updated 2 months ago
- ☆15Sep 1, 2025Updated last year
- ☆13Nov 19, 2023Updated 2 years ago
- Constructive Solid Geometry (CSG) and Quick Hull Library for golang☆10Oct 30, 2019Updated 6 years 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.
- 解锁自有 NVIDIA CMP 170HX / 90HX 的算力限制。Linux x86-64，需要 root。☆58Aug 6, 2026Updated 2 months ago
- vLLM fork for pascal gpu☆18Mar 13, 2026Updated 7 months ago
- Qwen3.8 Flash Next AWQ INT4 4x3090 v1: 262K, Vision, FP8 QSA KV and CUDA Graphs on 4x RTX 3090☆16Aug 30, 2026Updated last month
- An example of how we can move runtime components to a sub-directory in a .NET Core Standalone app☆11Sep 5, 2018Updated 8 years ago
- Dockerized environment to ease odoo development☆17Updated this week
- ☆18Feb 2, 2022Updated 4 years ago
- Script to normalize and validate STL files so that they play better with git version control.☆15Mar 15, 2021Updated 5 years ago
- Builds vLLM for ROCm gfx906 using Nix☆18Aug 29, 2026Updated 2 months ago
- ☆16Feb 1, 2021Updated 5 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Mediates between original client and server.☆10Oct 10, 2016Updated 10 years ago
- Linux NVIDIA GPU V/F Curve Editor☆96Mar 25, 2026Updated 7 months ago
- Russian language support for Ruby and Rails | Поддержка русского языка для Ruby и Rails☆20May 20, 2024Updated 2 years ago
- 小米路由器 4a 千兆版刷 OpenWRT / Xiaomi Router 4A Gigabit Flash OpenWRT☆13Jan 6, 2024Updated 2 years ago
- 2080ti TU102 doing the unlock trick☆128Oct 22, 2026Updated last week
- Rest AIP server for commuticate with Tion devices☆12Dec 19, 2020Updated 5 years ago
- We taught Claude how to drive Fusion 360. Sketches, extrusions, assemblies, exports—all through natural language. The hard part wasn't th…☆13Dec 17, 2025Updated 10 months ago