fmchisel: Efficient Compression and Training Algorithms for Foundation Models
☆90May 4, 2026Updated 4 months ago
Alternatives and similar repositories for fmchisel
Users that are interested in fmchisel are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A framework to meta-train transformers for causal ICL☆11Jul 15, 2026Updated 2 months ago
- DuaLip: Dual Decomposition based Linear Program Solver☆87May 13, 2026Updated 4 months ago
- LLM training parallelisms (DP, FSDP, TP, PP) in pure C☆29Jan 27, 2026Updated 7 months ago
- vLLM Daily Summarization of Merged PRs☆54Updated this week
- Cataloging released Triton kernels.☆312Sep 9, 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.
- Make triton easier☆49Sep 3, 2026Updated 3 weeks ago
- EleutherAI ML Performance reading group repository (slides, meeting recordings, annotated papers)☆37Mar 20, 2026Updated 6 months ago
- llama2 inference engine in Rust☆13Apr 12, 2024Updated 2 years ago
- [ICDCS 2023] Evaluation and Optimization of Gradient Compression for Distributed Deep Learning☆10Apr 28, 2023Updated 3 years ago
- Efficient Triton Kernels for LLM Training☆6,632Updated this week
- Framework for Algorithmic Correctness Testing of Operators☆17Mar 9, 2026Updated 6 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆12Nov 8, 2024Updated last year
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆2,632Updated this week
- ☆10Aug 18, 2016Updated 10 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆307Nov 7, 2025Updated 10 months ago
- ☆24Mar 7, 2025Updated last year
- Transforming Video Diffusion with Temporal Sparse Attention☆56Apr 8, 2026Updated 5 months ago
- Advancing the frontier of efficient AI☆69Sep 16, 2026Updated last week
- This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".☆145Aug 15, 2026Updated last month
- xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning☆34Jun 2, 2026Updated 3 months ago
- A Telegram bot to attach a banner about Yalda on your avatar.☆13Feb 10, 2023Updated 3 years ago
- KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches. EMNLP Findings 2024☆90Feb 27, 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.
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆331Jul 29, 2026Updated last month
- Training hybrid models for dummies.☆30Nov 1, 2025Updated 10 months ago
- ☆20May 20, 2025Updated last year
- 该六子棋程序使用Java语言编写,内置AI落子,主要由阿尔法贝塔搜索+评估函数实现,存在一定的bug,智能方面还行吧☆13Jul 24, 2021Updated 5 years ago
- ☆19Nov 11, 2025Updated 10 months ago
- QuantEase, a layer-wise quantization framework, frames the problem as discrete-structured non-convex optimization. Our work leverages Coo…☆20Feb 22, 2024Updated 2 years ago
- ☆13Oct 8, 2021Updated 4 years ago
- FM-Leaderboard-er allows you to create leaderboard to find the best LLM/prompt for your own business use case based on your data, task, p…☆19Oct 31, 2024Updated last year
- the frontend of lmcache☆18Apr 22, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- nv-one-logger enables tracking of GPU application progress over time and can help to identify overhead from workload and cluster ineffici…☆25Nov 6, 2025Updated 10 months ago
- Write a fast kernel and see how you compare against the best humans and AI on gpumode.com☆114Sep 18, 2026Updated last week
- Perplexity GPU Kernels☆608Nov 7, 2025Updated 10 months ago
- Replicache Diff Server☆14Mar 8, 2021Updated 5 years ago
- ☆29Jan 17, 2025Updated last year
- This repository implements the training, testing and evaluation code for the "VQ-NeRV: A Vector Quantised Neural Representation for Video…☆10Feb 19, 2024Updated 2 years ago
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆543Updated this week