qwen3
17 proyectos comparten este topic de GitHub
Las líneas conectan a los miembros que están mediblemente relacionados entre sí. El tamaño de los puntos refleja las estrellas.
🧬 Miembros
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 95.7k
MaxKB
🔥 MaxKB is an open-source platform for building enterprise-grade agents. …
★ 23k
ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4,…
★ 16k
GenieX
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
★ 8.5k
deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
★ 8.3k
Awesome-LLM-Inference
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4,…
★ 5.5k
Sidekick
A native macOS app that allows users to chat with a local LLM that can respond with information from files,…
★ 3.3k
WhisperJAV
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV
★ 2.4k
RCLI
Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG
★ 1.5k
MetaScreener
AI-powered tool for efficient abstract and PDF screening in systematic reviews.
★ 1.3k
halogen-flash-server
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models,…
★ 1.1k · GitHub ↗
llm-architecture-from-scratch
Implementing LLM architectures from scratch in PyTorch
★ 1.1k · GitHub ↗
MimikaStudio
MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support
★ 730
Qwen3-Medical-SFT
Qwen3 Fine-tuning: Medical R1 Style Chat
★ 330
LLM-TPU
Run generative AI models in sophgo BM1684X/BM1688
★ 311
AesCode
Aesthetic code generation with decoupled cross-modal rewards: turning prompts into editable, verifiable…
★ 187 · GitHub ↗
llama.cpp-v100
llama.cpp optimized for NVIDIA Tesla V100 (SM70): Qwen3.8-Flash-Next with MTP (prefill 3402 tok/s at 200K…
★ 59 · GitHub ↗
🔗 Familias relacionadas
Medido a partir de los temas de GitHub compartidos por ambos proyectos, ponderado por cuán raros son cada uno de los temas.