nvidia/GLM-5.2-NVFP4 · Discussions

Resources

View closed (3)

nvidia daddy , please update GLM5.3-flash-nvfp4

#12 opened 1 day ago by

Waiting for nvidia/GLM-5.3-NVFP4

#10 opened 3 days ago by

H200

#9 opened 7 days ago by

Even though the accuracy seems comparable, there is significant token inflation on a per task basis

#8 opened about 1 month ago by

tool_choice: "required" causes xgrammar FSM crash / infinite hang with GLM-5.2 on vLLM 0.24.0

#7 opened about 1 month ago by

How is the actual programming performance?

#6 opened about 2 months ago by

Some accuracy benchmark results are not as good as GLM-5.2-FP8

#5 opened 2 months ago by

Does it support MTP?

#4 opened 2 months ago by

Which version of VLLM should I use to run this checkpoint?

#2 opened 2 months ago by

gameofdimension

Can we use this model with nvfp4 kv cache?

#1 opened 2 months ago by