GLM-5.3-Flash (NVFP4) on 4× DGX Spark — Multi-Node TP4 Benchmark (5.3–7.0 tok/s)
#5 opened about 2 hours ago
by
tvearl
Deployment blocked: FlashInfer "Unsupported architecture" on DGX Spark (SM121)
1
#4 opened 1 day ago
by
JayceHuang
Sm120/rtx6000pro supported?
7
#3 opened 1 day ago
by
Quadrapole
B200 VLLM:glm53-flash
3
#2 opened 1 day ago
by
corgito
Is sglang supported?
1
#1 opened 1 day ago
by
botian