Project
- Stars
- Started
- Issues
- License
Run GLM locally on a pair of Tesla V100s
Run GLM-5.3-Flash with computation split between CPU and GPU. This Strata fork includes experimental two-GPU working profiles and checkpoint-inspection tools. Faster configurations use approximate runtime settings, so their output and performance depend on the chosen profile.
How did it go? Tips, problems, questions…
Run GLM locally on a pair of Tesla V100s
Run GLM-5.3-Flash with computation split between CPU and GPU. This Strata fork includes experimental two-GPU working profiles and checkpoint-inspection tools. Faster configurations use approximate runtime settings, so their output and performance depend on the chosen profile.

NVIDIA GPUs
58 followers · joined Apr 2014

NVIDIA GPUs
Not checked by defenders yet
Your agent will read all the code before installing anything
Feedback
How did it go? Tips, problems, questions…