Model: Support Step3.7-Flash by forforever73 · Pull Request #23845 · ggml-org/llama.cpp
A pull request has been submitted to the llama.cpp repository to add support for the Step3.7-Flash model. This integration aims to enable local execution of this particular AI model. The request also mentions ongoing work for Step-3.5-Flash support and inquires about future MTP support. AI
IMPACT Enables local execution of the Step3.7-Flash model on the llama.cpp framework.