The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; benchmarks vs llama.cpp in the README.
☆114Nov 7, 2026Updated this week
Alternatives and similar repositories for pxa
Users that are interested in pxa are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Superseded by github.com/poisonxa16/pxa — PXA, the set-and-forget engine for Pascal and Volta☆24Sep 8, 2026Updated last month
- llama.cpp tuned for 2x Tesla P100 (sm_60). Decode 1.86x, 3-4x with MTP (up to ~70 t/s on code). Prefill 2x, full 262k context with vision…☆46Updated this week
- LLM inference in C/C++☆22Oct 25, 2026Updated last week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆260Sep 14, 2026Updated last month
- V100 / SM70-focused vLLM engineering fork for modern LLM inference.☆1,477Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Toolkit for optimizing or building inference engines tailored to your hardware and desired LLM.☆44Updated this week
- Strata port for Tesla V100 (sm_70): Qwen3.8-Flash-Next with 262K context and MTP☆129Updated this week
- CUDA engine that splits every layer of a production quality MoE LLM across three PCIe V100 cards delivering 382 tok/s on a used $1,800 bo…☆64Updated 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
- Third party commentaries for UniqueBible☆13Apr 8, 2021Updated 5 years ago
- SGLang for cool dudes using V100☆84Updated this week
- 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
- ☆15Oct 18, 2026Updated 2 weeks ago
- Production-grade convergence & anti-overthinking steering extension for Pi Coding Agent (tuned for Bonsai 2 / Qwen)☆18Sep 21, 2026Updated last month
- 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.
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆33Aug 29, 2026Updated 2 months ago
- Lightning-fast kernel dispatch for ROCm. Retained command replay over public ROCr/HSA queues.☆15Oct 11, 2026Updated 3 weeks ago
- More MoEs: a fork of Strata (Qwen3.8-Flash-Next, Qwen3.6/Ornith and more on one GPU + system RAM)☆25Updated this week
- Agentic-coding oriented inference engine for N x V100-SXM2, based on SGLang: GLM-5.3-Flash, Qwen3.8-Flash-Next, DeepSeek-V4.1-Flash, Mini…☆35Oct 7, 2026Updated last month
- High-performance Duo-V100-GPU inference for selected model checkpoints and GPUs.☆37Updated this week
- ☆18Jan 3, 2026Updated 10 months ago
- LLM inference in C/C++☆29Updated this week
- DELL T5810 OpenCore (Monterey/Ventura/Sonoma Support)☆27Jul 6, 2025Updated last year
- Run Qwen3.8-Flash-Next on one AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). EXL3 4.05 and 3.05 bpw packs, own ROCm/HIP kernels, OpenAI-com…☆19Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆23Jul 10, 2026Updated 3 months ago
- Implementation of FlashAttention-2 for Nvidia Tesla V100 / Titan V☆217Updated this week
- A daemon that automatically manages the performance states of NVIDIA GPUs.☆171Feb 24, 2026Updated 8 months ago
- Tutorial and test projects for the ZPUFlex core.☆11Dec 4, 2021Updated 4 years ago
- A coding agent built on LLM☆38Jul 4, 2026Updated 4 months ago
- A CLI tool that can convert LiDAR LAS files to STL files for 3D printing or rendering as terrain☆11Jun 24, 2026Updated 4 months ago
- A 198t/s and 353t/s qwen 3.8 27b inferencing engine for 2*v100 and 4*v100☆101Updated this week
- FastFlow-SDK is a software stack for running and developing applications on AMD XDNA Neural Processing Engines (NPUs).☆14Updated this week
- ☆15Jul 1, 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.
- Replica of the 8088 processor card for the CBM-II computers☆10Mar 4, 2021Updated 5 years ago
- A collection of utility scripts for managing Ollama models on Linux systems. These tools help simplify common administration tasks for yo…☆13Aug 27, 2026Updated 2 months ago
- Unified terminal monitor for AMD Ryzen AI NPU (XDNA) + iGPU — live utilization for Strix Halo, where amd-smi comes up empty☆40Oct 18, 2026Updated 2 weeks ago
- llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ to…☆267Updated this week
- The main repository for building Pascal-compatible versions of ML applications and libraries.☆220Aug 23, 2025Updated last year
- Volkswagen Audi Group VWTP 2.0 Diagnostic Simulator☆12Jun 3, 2017Updated 9 years ago
- Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthrop…☆1,253Updated this week