Benchmarking Intelligence Efficiency of LM Inference
☆95Sep 9, 2026Updated 3 weeks ago
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☆33Sep 18, 2026Updated 2 weeks ago
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention☆23May 25, 2026Updated 4 months ago
- ☆17Mar 21, 2026Updated 6 months ago
- Numerical Methods in Macroeconomics and Finance using Python (NHH, spring 2026)☆17Apr 8, 2026Updated 5 months ago
- An MLX implementation of Meta AI's ESM-2 protein language model☆16Aug 16, 2025Updated last year
- 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.
- Minimalist repo to do mlx vlm constrained decoding in batch mode☆19Apr 11, 2026Updated 5 months ago
- ☆49Jan 3, 2026Updated 9 months ago
- A series of high-performance GEMM (General Matrix Multiply) implementations Iteratively optimised for H100 GPUs in Pure CUDA.☆83Feb 18, 2026Updated 7 months ago
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Mar 30, 2026Updated 6 months ago
- ☆19Mar 29, 2026Updated 6 months ago
- Implementation of ModernBERT in MLX☆21Jan 7, 2026Updated 8 months ago
- learning & making kernels in cuda / triton☆22Aug 24, 2025Updated last year
- ☆32Sep 4, 2025Updated last year
- ☆15Jan 24, 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.
- ☆565Updated this week
- a fast and lightweight distributed background task processing framework with seamless scheduling.☆15Mar 30, 2026Updated 6 months ago
- ScaleRL Curve Fitting☆17Oct 13, 2025Updated 11 months ago
- Optimized GPU compiler for LLM inference. Choose from a list of optimized recipes or optimize your own model via kernel fusion, autotunin…☆82Updated this week
- ☆12Jan 16, 2025Updated last year
- Generate MoonBit bindings from TypeScript definitions via the TypeScript compiler API☆11Jul 29, 2025Updated last year
- Julia code for an upper level undergraduate macroeconomics course.☆10May 18, 2022Updated 4 years ago
- Embedding Recycling for Language models☆38Jul 11, 2023Updated 3 years ago
- Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200☆124Feb 28, 2026Updated 7 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.
- A WebAssembly eBPF runtime based on wasmtime in rust☆11Feb 20, 2023Updated 3 years ago
- ☆10Feb 17, 2024Updated 2 years ago
- ☆57Mar 18, 2026Updated 6 months ago
- Data Parallel Programming, the 2022 edition☆12Jan 18, 2024Updated 2 years ago
- Pixels, Patterns, but no Poetry: To See the World like Humans☆18Aug 11, 2025Updated last year
- NVFP4 Flash-Attention 4 on BlackWell☆67Updated this week
- A curated biochemical database that integrates and refines data from KEGG and ATLAS databases to support precise analyses of biochemical …☆16May 13, 2026Updated 4 months ago
- Artifact for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆47Nov 24, 2022Updated 3 years ago
- ☆15Nov 19, 2025Updated 10 months ago
- 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.
- An OpenAI API Compatible Honeypot Gateway☆27Mar 17, 2025Updated last year
- ☆15Jan 27, 2025Updated last year
- minimal Energy-based transformer☆44Dec 11, 2025Updated 9 months ago
- ☆10Jul 10, 2023Updated 3 years ago
- ☆16Oct 21, 2025Updated 11 months ago
- A benchmark to measure AI progress on unsolved research problems in mathematics.☆35Sep 26, 2026Updated last week
- The official code of "VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation" [EMNLP25]☆19Sep 21, 2025Updated last year