Benchmarking Intelligence Efficiency of LM Inference
☆98Oct 15, 2026Updated last week
Alternatives and similar repositories for intelligence-per-watt
Users that are interested in intelligence-per-watt are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Dynamic per-token early exit for LLM inference. Skip layers tokens don't need☆34Sep 18, 2026Updated last month
- ☆24Oct 8, 2026Updated 2 weeks ago
- A collection of Pythonic subword tokenisers and text preprocessing tools.☆15Updated this week
- ☆32Sep 4, 2025Updated last year
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention☆24May 25, 2026Updated 4 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆219Mar 7, 2025Updated last year
- Code for the paper "Greed is All You Need: An Evaluation of Tokenizer Inference Methods"☆15Sep 2, 2026Updated last month
- How Post-Training Shapes Biological Reasoning Models☆17Jun 16, 2026Updated 4 months ago
- Prefix Sliding for efficient test-time scaling☆27Oct 16, 2026Updated last week
- MLX binary vectors and associated algorithms.☆14Mar 13, 2025Updated last year
- FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.☆112Jul 18, 2026Updated 3 months ago
- Big & Small LLMs working together☆1,376Mar 12, 2026Updated 7 months ago
- An MLX implementation of Meta AI's ESM-2 protein language model☆16Aug 16, 2025Updated last year
- ☆19Mar 29, 2026Updated 6 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code for ICML 2025 paper | Joint Localization and Activation Editing for Low-Resource Fine-Tuning☆28Jun 18, 2025Updated last year
- ☆49Jan 3, 2026Updated 9 months ago
- GPU-accelerated Schulze voting method in Python, Numba, CUDA, and Mojo 🔥, using ideas from Algebraic Graph Theory☆19Oct 6, 2026Updated 2 weeks ago
- ☆132Sep 25, 2024Updated 2 years ago
- Minimalist repo to do mlx vlm constrained decoding in batch mode☆20Apr 11, 2026Updated 6 months ago
- Sequential Monte Carlo Speculative Decoding☆54Aug 25, 2026Updated last month
- learning & making kernels in cuda / triton☆22Aug 24, 2025Updated last year
- ☆11Oct 9, 2023Updated 3 years ago
- A step by step guide to fine-tuning the DeepSeek R1 Distilled models on Apple Silicon machines.☆60Feb 1, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- SDK-first orchestration platform for managing AI coding agent fleets: BYOA key rotation, real-time WebSocket dashboard, DCG integration, …☆24Updated this week
- Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200☆124Feb 28, 2026Updated 7 months ago
- Cross-platform Rust daemon that prevents disk-full incidents for AI coding workloads using predictive pressure control, safe artifact cle…☆31Updated this week
- Generate MoonBit bindings from TypeScript definitions via the TypeScript compiler API☆11Jul 29, 2025Updated last year
- herdr-gamepad fork: full Xbox Series X|S support (hat-switch D-pad, triggers, Share) + a Claude Code supervisor layout☆10Sep 9, 2026Updated last month
- AI podcast summary from a youtube video using Anthropic or XAI and Elevenlabs voices☆11Oct 21, 2025Updated last year
- A multipurpose Fortran2003+MPI suite of codes for the simulation of spin dynamics at the atomistic level. The code is developed to readil…☆13Jul 16, 2025Updated last year
- ☆83Apr 26, 2026Updated 5 months ago
- Simple, flexible configuration in pure Python!☆32Jul 1, 2025Updated last year
- 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.
- A series of high-performance GEMM (General Matrix Multiply) implementations Iteratively optimised for H100 GPUs in Pure CUDA.☆83Feb 18, 2026Updated 8 months ago
- Bayesian process classifier that detects abandoned/zombie processes and recommends safe cleanup actions☆29Oct 15, 2026Updated last week
- Pixels, Patterns, but no Poetry: To See the World like Humans☆18Aug 11, 2025Updated last year
- Code for 'Answer Matching Outperforms Multiple Choice for Language Model Evaluation' paper☆20Jul 4, 2025Updated last year
- ☆648May 24, 2026Updated 4 months ago
- ☆15Nov 19, 2025Updated 11 months ago
- ☆17Apr 2, 2026Updated 6 months ago