StartLux-Decision
+387Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
inference
AI & Machine LearningChủ đề #inference trên GitHub — repository trong kho Beeknoee có gắn topic này.
- Repository
- 106
- Tổng sao
- 818.4k
- 24 giờ
- +0.1%
- 7 ngày
- +0.6%
- 30 ngày
- +2.1%
Repository trong #inference
trymirai/uzu
+453A high-performance inference engine for AI models
T-Crypt/berth
+100Decides who gets your GPU. Chat, image and voice engines lease the card in turn instead of grabbing it, so two of them never load at once and crash each other. One Go binary, nothing else to install.
sglang
+703SGLang is a high-performance serving framework for large language models and multimodal models.
Remory
+165Remory: Learning Residual Memory for Context Compaction
vllm
+638A high-throughput and memory-efficient inference and serving engine for LLMs
FreeVideo
+175Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
whisper.cpp
+170Port of OpenAI's Whisper model in C/C++
faster-whisper
+206Faster Whisper transcription with CTranslate2
Chủ đề khác
Cùng danh mục AI & Machine Learning và các chủ đề phổ biến khác trong kho Beeknoee
