# Native MoE engines — ds4 (DeepSeek-V4, CUDA), colibri (GLM-5.2 CUDA;
# DeepSeek-V4 and Kimi-K3 CPU) and kimi-k3-in-c — a coderai pod that serves
# frontier-size models through the same C engines the local install uses.
#
# The engines are not pip packages: they are compiled in a CUDA 12.8 toolchain
# stage of Dockerfile.capability-engines (see the `engines.dockerfile` marker)
# for EVERY pod GPU generation (sm_80/86/89/90/120a), not the one card this
# machine has, and copied in beside their download scripts.
#
# LIGHT core: the engines are C binaries and coderai only drives them, so the
# 5 GB of torch in the full core would be dead weight. All they link is the
# CUDA runtime and cuBLAS, which NVIDIA ships as wheels — 12.8 to match the
# toolchain they were compiled with. The engines bring their own tokenizers.
nvidia-cuda-runtime-cu12==12.8.90
nvidia-cublas-cu12==12.8.4.1
#
# THE WEIGHTS ARE THE COST. DeepSeek-V4 is ~154 GB, Kimi-K3 is measured in
# terabytes. Put them on a network volume (docs/runpod.md, "Engine pods") —
# a pod without one downloads all of it on every cold start.
sentencepiece>=0.1.99
protobuf>=3.20.0
