🌴
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 streaming runtime for Fish Audio S2-Pro on NVIDIA DGX Spark
C 1
-
dsv4-flash-b300
dsv4-flash-b300 PublicOne-click RunPod template: DeepSeek-V4-Flash-0731 (abliterated) on one NVIDIA B300 — vLLM, DSpark-7 speculative decoding, native Anthropic Messages API for Claude Code
Shell
-
gptoss-spark
gptoss-spark Publicgpt-oss-120b on one NVIDIA DGX Spark at 65 tok/s single-stream and 300 tok/s aggregate at 30 users — five patches on upstream vLLM plus SM121 CUTLASS MXFP4 kernels, with the full measurement campai…
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.




