You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Run zai-org/GLM-5.3-Flash as an EXL3 4bpw checkpoint on NVIDIA DGX Spark (GB10) with vLLM and cuda-exl3 — measured two-node (TP=2) and three-node (TP=3 + expert parallel) recipes, plus the kernel f…