Lossless compression of BF16 MLP weights for LLM inference on NVIDIA Hopper GPUs
☆59Apr 17, 2026Updated 7 months ago
Alternatives and similar repositories for unweight-kernels
Users that are interested in unweight-kernels are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆20Sep 28, 2024Updated 2 years ago
- Ready-to-use harnesses for OpenReward environments☆13Sep 21, 2026Updated last month
- The official baseline implementations for Chronocept. Published at EACL 2026.☆10Aug 4, 2026Updated 3 months ago
- FlashInfer+ROCm: ROCm port of FlashInfer☆13Updated this week
- REAP expert pruning for MoE LLMs on Apple Silicon via MLX☆58Mar 16, 2026Updated 8 months 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.
- ☆18Jul 1, 2025Updated last year
- Generate beautiful, standalone HTML interfaces for your ComfyUI workflows with just a few clicks!☆20Jul 24, 2026Updated 3 months ago
- ☆63Dec 19, 2025Updated 11 months ago
- Weakly Supervised Object Localization via Class RE-Activation Mapping☆12Sep 19, 2022Updated 4 years ago
- 🎮 Material You TUI for monitoring NVIDIA GPUs☆58Jan 16, 2026Updated 10 months ago
- Samples of various features of LittleKt☆16Nov 12, 2026Updated last week
- Kubernetes Pod File System Explorer☆12Feb 12, 2024Updated 2 years ago
- ☆16Jul 23, 2026Updated 3 months ago
- ☆25Jun 12, 2025Updated last year
- 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.
- Firecrawl-backed web_search and web_fetch providers for the DeepSeek Harness web capability seam (ctx.web)☆18Oct 21, 2026Updated 3 weeks ago
- Validation / Sanitization library for node, with a clean & functional API☆12Apr 16, 2013Updated 13 years ago
- ☆16Oct 25, 2026Updated 3 weeks ago
- build of ffmpeg.wasm specifically for converting H.265 (HEVC) video to H.264 (AVC)☆24Jan 7, 2025Updated last year
- ☆12May 11, 2025Updated last year
- Converts Minecraft Map Or Schematic To Hytale Map Or Schematic☆13Jan 20, 2026Updated 9 months ago
- KV cache middleware for 1M context on 12GB VRAM. Uses K vectors as a retrieval index to fetch V on-demand from system RAM. No model modif…☆11Apr 23, 2026Updated 6 months ago
- A simple streamlit app to play with qwen3-2b-VL to perform OCR. Dockerized set up, tested with 3060 12 GB.☆32Nov 23, 2025Updated 11 months ago
- 🚀 LLaVA-FastVLM: One-Click Visual Language API☆15Jun 14, 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.
- 100% MFU or bust.☆11Jan 12, 2026Updated 10 months ago
- An execution-driven, cycle-accurate GPU simulator for modern architectures and AI workloads.☆68Updated this week
- A class for synchronizing sensor readings to the system clock☆11Oct 25, 2018Updated 8 years ago
- A systems programming language where automatic differentiation is a compiler pass and model parameters are explicit, growable memory.☆27Jan 5, 2026Updated 10 months ago
- Specialized AI agents for your bare metal. 100% On-Prem & Air-Gap ready.☆25Feb 21, 2026Updated 8 months ago
- A Conversational Speech Generation Model☆15Mar 16, 2025Updated last year
- ☆13Jan 16, 2019Updated 7 years ago
- Official code repository for "Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse [VLDB 25]"☆12Jul 8, 2026Updated 4 months ago
- Run Qwen3.8-27B from 13 GB of RAM (4-bit) with ~1% quality loss☆11Aug 27, 2026Updated 2 months 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.
- Windows microphone booster - boost your mic volume up to 500%☆16Mar 20, 2026Updated 7 months ago
- Nanochat in MLX☆12Mar 6, 2026Updated 8 months ago
- Example of applying CUDA graphs to LLaMA-v2☆11Aug 25, 2023Updated 3 years ago
- ☆13Aug 26, 2024Updated 2 years ago
- Tool for detecting bad style in Standard ML programs☆17Mar 10, 2019Updated 7 years ago
- Nexusflow function call, tool use, and agent benchmarks.☆28Dec 13, 2024Updated last year
- Modular and structured prompt caching for low-latency LLM inference☆13May 12, 2024Updated 2 years ago
Are these results useful?