deepseek-v3

7 projets partagent ce topic GitHub

Les traits relient les membres réellement apparentés entre eux. La taille des points suit les étoiles.

🧬 Membres

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

★ 95.7k

Awesome-LLM-Inference

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4,…

★ 5.5k

xtuner

A Next-Generation Training Engine Built for Ultra-Large MoE Models

★ 5.2k

llm-architecture-from-scratch

Implementing LLM architectures from scratch in PyTorch

★ 1.1k · GitHub ↗

LightCompress

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video…

★ 751

OmniThink

[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

★ 485

codai

AI coding agent for your terminal.

★ 377

Mesuré à partir des topics GitHub communs aux deux projets, pondérés par leur rareté.