Lists (2)
Starred repositories
Tinymist [ˈtaɪni mɪst] is an integrated language service for Typst [taɪpst].
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Run Claude Code in Obsidian
Open-source framework for the research and development of foundation models.
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
All the mods skyblock pack for 1.21.1 NeoForge
🔥 A minimal training framework for scaling FLA models
[ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
A paper list for spatial reasoning
Hackable and optimized Transformers building blocks, supporting a composable construction.
Specification and documentation for Agent Skills
Making large AI models cheaper, faster and more accessible
Measure and optimize the energy consumption of your AI applications!
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE"
A terminal assistant that allows you to ask an LLM to run commands.
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
SGLang is a high-performance serving framework for large language models and multimodal models.
3x Faster Inference; Unofficial implementation of EAGLE Speculative Decoding
Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)