Repository Index

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

• kv-cache
• llm-inference
• local-llm
• quantization

Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.

• cuda
• ggml
• low-vram
• speech-synthesis

基于 PatchCore 的工业异常检测项目，研究 layer2/layer3 分数融合、敏感性引导收缩与风险受控门控，并提供 Streamlit 工程化 Demo。

• anomaly-detection
• computer-vision
• feature-fusion
• industrial-anomaly-detection

Fish Audio Drama 3 text-to-speech on the TensorFold native CUDA engine for DGX Spark (GB10): recipe, engine patches, benchmarks. Built with Fish Audio.