Popular repositories Loading
-
qwen-3.8-next-flash-amd-strix-halo
qwen-3.8-next-flash-amd-strix-halo PublicServing Qwen3.8-Flash-Next on a single AMD Strix Halo (Ryzen AI MAX+ 395, gfx1151, 128 GB unified memory)
Python 11
-
nvidia-spark-skills
nvidia-spark-skills PublicSkills for Managing and Operating a twin Spark Set-up (based on my twin Lenovo ThinkStation PGX Setup).
-
Deepseek-v4.1F-TensorShard
Deepseek-v4.1F-TensorShard PublicTensorShard helps a pair of DGX Sparks retain more agent context and resume work with less repeated prefill. It combines a tuned TensorFold serving recipe, unequal KV ownership and NVMe-backed rest…
-
fluid-decisions-v-1
fluid-decisions-v-1 PublicPolicy and adapters in front of two d1 decision lanes: the model answers typed questions, policy code decides the action. v0.1.0 (thresholds uncalibrated).
Python 2
-
roo-voice-tts
roo-voice-tts PublicRoo Voice — local, reference-conditioned single-voice TTS. One-click app + models for Apple MLX, NVIDIA CUDA, AMD Vulkan/ROCm, and NPU (ONNX).
-
glm-5.3-flash-exl3-prod
glm-5.3-flash-exl3-prod PublicGLM-5.3-Flash EXL3 4bpw on 2x NVIDIA DGX Spark (GB10): production recipe, boot ladder, quality gate, benchmarks and lessons learned — reproducible from CLAUDE.md/AGENTS.md
Python 1
If the problem persists, check the GitHub status page or contact support.