LLM Inference on consumer devices
☆130Mar 17, 2025Updated last year
Alternatives and similar repositories for UMbreLLa
Users that are interested in UMbreLLa are comparing it to the libraries listed below
Sorting:
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆18Feb 9, 2026Updated last month
- scalable and robust tree-based speculative decoding algorithm☆372Jan 28, 2025Updated last year
- 🚀 FlexLLama - Lightweight self-hosted tool for running multiple llama.cpp server instances with OpenAI v1 API compatibility and multi-GP…☆52Mar 5, 2026Updated 2 weeks ago
- ☆27Jun 11, 2025Updated 9 months ago
- ☆24Jan 22, 2025Updated last year
- Simple python library for generating your own perfetto traces for your application. Can be used for both app instrumentation and custom …☆25Jun 22, 2025Updated 8 months ago
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated 9 months ago
- ☆17Dec 16, 2024Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆148Dec 23, 2025Updated 2 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆49Jan 21, 2026Updated 2 months ago
- Super simple python connectors for llama.cpp, including vision models (Gemma 3, Qwen2-VL). Compile llama.cpp and run!☆29Dec 11, 2025Updated 3 months ago
- A local-first LLM development studio. Build, test, and customize inference workflows with your own models — no cloud, totally local.☆17May 21, 2025Updated 10 months ago
- Collaborative inference of latent diffusion via hivemind☆12May 29, 2023Updated 2 years ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆75Sep 15, 2025Updated 6 months ago
- Lightweight Python Wrapper for OpenVINO, enabling LLM inference on NPUs☆27Dec 17, 2024Updated last year
- A forward proxy to turn network traffic into personal memory for AI agents☆36Updated this week
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Sep 10, 2024Updated last year
- a simple API to use CUPTI☆10Aug 19, 2025Updated 7 months ago
- Simple node proxy for llama-server that enables MCP use☆18May 10, 2025Updated 10 months ago
- A lightweight LLaMA.cpp HTTP server Docker image based on Alpine Linux.☆32Oct 3, 2025Updated 5 months ago
- ☆20Nov 26, 2025Updated 3 months ago
- ☆78Nov 26, 2024Updated last year
- Simulation, multi-path estimation, and CBR parsing code of SIGCOMM2023 BeamSense CBR-Sensing☆10Jan 14, 2024Updated 2 years ago
- Test your local LLMs on the AIME problems☆32Jun 7, 2025Updated 9 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆293Mar 10, 2026Updated last week
- AI management tool☆121Nov 9, 2024Updated last year
- Adding a multi-text multi-speaker script (diffe) that is based on a script from asiff00 on issue 61 for Sesame: A Conversational Speech G…☆26Mar 28, 2025Updated 11 months ago
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆31May 1, 2025Updated 10 months ago
- This is official project in our paper: Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers☆31Jan 13, 2024Updated 2 years ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆372Apr 22, 2025Updated 10 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆251Dec 16, 2024Updated last year
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆56Feb 10, 2025Updated last year
- "Le refuge" is a consciousness emulation module for all LLMs.☆41Mar 11, 2026Updated last week
- A cross platform App that gives you the best UX to run models locally or remotely on your own hardware☆75Updated this week
- A slurm solution for Crusoe Cloud☆14Mar 5, 2026Updated 2 weeks ago
- ☆64Dec 3, 2024Updated last year
- Testing LLM reasoning abilities with family relationship quizzes.☆63Jan 28, 2025Updated last year
- Yet another frontend for LLM, written using .NET and WinUI 3☆10Sep 14, 2025Updated 6 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆54Mar 14, 2025Updated last year