TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fallback.
☆81Sep 19, 2026Updated 2 weeks ago
Alternatives and similar repositories for turboquant-vllm
Users that are interested in turboquant-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:
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆232Updated this week
- forked from vllm-project/flash-attention☆66May 9, 2026Updated 4 months ago
- Nano vLLM☆25Aug 11, 2025Updated last year
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆133Updated this week
- Unlock P2P comms between consumer NVIDIA GPUs☆559Sep 16, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆19May 10, 2026Updated 4 months ago
- Native app wrapper for Chatto, adding system tray, notifications, auto-start, deep link support☆14Sep 23, 2026Updated last week
- Run SGLang on 1-to-N NVIDIA DGX Spark servers (single Spark, 2 via direct cable, or 3+ via switched fabric) to serve or benchmark LLMs☆21May 1, 2026Updated 5 months ago
- NEW ROCmfp4 format for llama.cpp☆157Jun 13, 2026Updated 3 months ago
- HTTP Proxy that allows you to define the IP address at connect time☆20Jan 11, 2026Updated 8 months ago
- Workshop that will take you from Graph Neural Networks (GNNs) to Transformers, architectures which have led to numerous breakthrough achi…☆12Sep 11, 2023Updated 3 years ago
- FastAPI wrapper around original Vibevoice 1.5B and 7B models, with support for AWQ4 quant☆33Jun 22, 2026Updated 3 months ago
- A Hermes UI☆22Aug 9, 2026Updated last month
- Electron speech-to-speech app for your voice calls based on 100% locally run AI models☆36Jul 23, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆42Nov 13, 2025Updated 10 months ago
- vLLM TurboQuant☆618Jun 25, 2026Updated 3 months ago
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆409Sep 23, 2026Updated last week
- An Enhanced TOP program to monitor your Nvidia DGX SPARK's Hardware☆37Jan 6, 2026Updated 8 months ago
- AI医生☆10May 27, 2020Updated 6 years ago
- Transformer creation from scratch using Jax.☆20Dec 8, 2024Updated last year
- Chatbot_CN项目的知识图谱模块☆12Mar 27, 2020Updated 6 years ago
- Experimental llama.cpp fork for inference research and development☆879Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆3,272Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆13Oct 10, 2024Updated last year
- Experiments codes for COLING '22 paper "Augmenting Legal Judgment Prediction with Contrastive Case Relations"☆11Apr 25, 2024Updated 2 years ago
- OpenCode local AI provider setup with automatic model syncing for LM Studio, vLLM, Ollama and any OpenAI-compatible API☆42Jul 10, 2026Updated 2 months ago
- ☆17Aug 13, 2026Updated last month
- LLM inference in C/C++☆35Aug 24, 2026Updated last month
- Replayable Browser Agent☆17Apr 24, 2026Updated 5 months ago
- Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors e…☆102Updated this week
- ☆20Oct 25, 2025Updated 11 months ago
- An Opencode plugin for managing git worktrees.☆77Updated this 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.
- Acceleration codes for the Ozaki-scheme on integer matrix multiplication units.☆27Dec 10, 2025Updated 9 months ago
- MCP as a Judge is a behavioral MCP that strengthens AI coding assistants by requiring explicit LLM evaluations☆17Dec 15, 2025Updated 9 months ago
- a fast and lightweight distributed background task processing framework with seamless scheduling.☆15Mar 30, 2026Updated 6 months ago
- Distributed Inference for mlx LLm☆104Aug 1, 2024Updated 2 years ago
- ☆47May 7, 2026Updated 4 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆22Updated this week
- ☆19Aug 22, 2026Updated last month