Skip to content
View beastllama's full-sized avatar
😁
changing the world line by line. I own a minivan... don't judge me!
😁
changing the world line by line. I own a minivan... don't judge me!
2 followers · 3 following

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: YOLO

Block or report beastllama

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. GLM-5.3-Flash-DFlash2-SGLang-2x-DGX-Spark GLM-5.3-Flash-DFlash2-SGLang-2x-DGX-Spark Public

    GLM-5.3-Flash (320B) + DFlash2 speculative decoding on SGLang TP=2, 2x NVIDIA DGX Spark (GB10) — first published SGLang recipe: 4 day-0 fixes, patched image, probes, honest first-light numbers (1.8…

    Python 9

  2. dgx-spark-qwen38-flash-next-recipe dgx-spark-qwen38-flash-next-recipe Public

    Recipe + field notes: Qwen3.8-Flash-Next NVFP4 on 2x DGX Spark (GB10), SGLang TP=2. Config delta on MiaAI-Lab's base stack, the multi-node deadlock behind a default-deny firewall, page cache as the…

    Python 3