zai-org
/

GLM-4.7-Flash

Text Generation

Model card Files Files and versions

Resources

View closed (0)

llama.cpp inference - 20 times (!) slower than OSS 20 on a RTX 5090

#12 opened about 4 hours ago by

FlashX

#11 opened about 4 hours ago by

We are so back!

#10 opened about 5 hours ago by

The adaptation for SGLang is being processed.

#9 opened about 6 hours ago by

Is a dedicated Tech Report planned for GLM-4.7-Flash?

#8 opened about 6 hours ago by

FP8

#7 opened about 6 hours ago by

Recommended sampling parameters

#6 opened about 6 hours ago by

DeepseekV3ForCausalLM

#5 opened about 6 hours ago by

Thank you!

#4 opened about 7 hours ago by

Enormous KV-cache size?

#3 opened about 7 hours ago by

Base model

#2 opened about 7 hours ago by

Performance Discussion

#1 opened about 7 hours ago by