🌴
On vacation
i build ai tools, infra, and other nerdy stuff. most serious projects are private on gh — open for projects, dm if interested.
Highlights
- Pro
Pinned Loading
-
s2pro-native
s2pro-native PublicNative C and CUDA runtime for Fish Audio S2-Pro text-to-speech on NVIDIA DGX Spark
C 1
-
dsv4-flash-b300
dsv4-flash-b300 PublicDeepSeek-V4-Flash (abliterated) serving image for one NVIDIA B300 on RunPod, with Anthropic and OpenAI APIs
Shell 1
-
gptoss-spark
gptoss-spark Publicgpt-oss-120b on one NVIDIA DGX Spark at 68.9 tok/s single-stream and 300 tok/s at 30 users, using six patches on vLLM and SM121 CUTLASS MXFP4 kernels.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.




