Popular repositories Loading

1. titanvault-minutes titanvault-minutes Public

   录音转写与会议纪要 · 自部署 Web 版 · GPU 加速 · 隐私优先 · Recording transcription & meeting notes self-hosted web app

   Python 13 3

2. TitanVault TitanVault Public

   A turnkey, fully-local AI workstation engineered for the AMD Ryzen AI Max+ 395. LLM inference, voice, document parsing, browser automation, agents — all on-device.

   Python 7 2

3. dsv41-flash-pp4-170hx dsv41-flash-pp4-170hx Public

   DeepSeek-V4.1-Flash (764B) on 4×CMP 170HX: PP4 + shadow KV + EXL3 2bpw + DSpark + 512k ctx + native vision — patches, recipes, acceptance bench, honest findings

   Python 7 1

4. dsv4-vision-170hx dsv4-vision-170hx Public

   DeepSeek-V4-Flash-Vision-Exp multimodal serving on 4× CMP 170HX (unlocked GA100, sm_80, PP4, 512k ctx, DSpark)

   Python 4 4

5. comfyui-illustration-skill comfyui-illustration-skill Public

   Python 1

6. glm53-flash-170hx glm53-flash-170hx Public

   GLM-5.3-Flash (320B MoE) production serving on 4x CMP 170HX: PP4 + EXL3 4bpw + Marlin INT4 sidecar + DFlash2 k=7 adaptive verification length, 512K context, ~4.5M-token tiered KV pool (GPU + 128GiB…

   Python 1 1