Curious on all things surrounding digital forensics, static/dynamic malware analysis, reverse engineering, CTFs, scripting, programming, and more!
- Michigan
-
03:50
(UTC -05:00)
Pinned Loading
-
qwen3.8-Flash-DGX-UltraFast
qwen3.8-Flash-DGX-UltraFast PublicForked from dime-online/qwen3.8-Flash-DGX-UltraFast
Qwen3.8 Flash at 74 tok/s on a single DGX Spark / GB10. vLLM + MTP recipe, 212 tok/s at 8 streams.
Python
-
qwen38-flash-next-nvfp4-spark
qwen38-flash-next-nvfp4-spark PublicForked from Radar105/qwen38-flash-next-nvfp4-spark
Qwen3.8 Flash Next NVFP4 on one GB10: 262K context, BF16 KV, MTP2 and verified prefix caching.
HTML
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.