- San Jose, CA
- https://linkedin.com/in/adubkov/
Pinned Loading
-
qwen38-flash-next-rtx-pro-6000-replicas
qwen38-flash-next-rtx-pro-6000-replicas PublicQwen3.8-Flash-Next (180B-A10B, NVFP4) as two TP1 replicas on 2x RTX PRO 6000 Blackwell with one shared pinned PLE table: deployable config, plugin, bench harnesses, measured record
Python
-
glm53-flash-rtx-pro-6000-tp2-ep2
glm53-flash-rtx-pro-6000-tp2-ep2 PublicGLM-5.3-Flash (W4A16 NVFP4-K32) on 2× RTX PRO 6000 Blackwell 96 GB (SM120) over PCIe: TP2 + EP2 — 288 routed experts split 144/rank.
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.