# Authoritative build inputs — GLM-5.3-Flash r12 (jovian-judgement) clean build.
# Every entry is a tag or exact version — no :latest, no main, no ranges.
# Pattern: solar-open2-nvfp4 (raw CUDA base, staged wheel builds, ccache/uv
# buildx caches) — content r12-specific per the rtx6kpro source contract.

# CUDA base (aarch64; digest-pinned, tested by solar-open2-nvfp4)
CUDA_BASE_IMAGE=nvidia/cuda:13.2.0-devel-ubuntu24.04
CUDA_BASE_DIGEST=sha256:a5b6256e470196fc1d5f8f62139d57d3662867746dfe1cb352d7652024047020

# Python / uv
UV_VERSION=0.11.28
PYPI_INDEX_URL=https://pypi.org/simple
PYTORCH_INDEX_URL=https://download.pytorch.org/whl/cu130

# Torch stack — the fork's requirements/cuda.txt pins (r12 era, cu130 aarch64)
TORCH_VERSION=2.13.0
TORCHVISION_VERSION=0.28.0
TORCHAUDIO_VERSION=2.11.0

# FlashInfer — the fork's cuda.txt uses flashinfer-python==0.6.17 (PyPI);
# flashinfer-cubin is NOT a build dep (setup.py skips it; the runtime
# fetches cubins when the package is absent).
FLASHINFER_VERSION=0.6.17

# vLLM — local-inference-lab fork, dev/jovian-judgement base + PR heads
VLLM_REPO=https://github.com/local-inference-lab/vllm.git
VLLM_BASE_REF=54f6e9826c20ef06ed65d838c0ad497ad0abdecf
VLLM_PRS="550 552 553 554 555 557"

# B12X — master + PR heads (pure-python wheel; CuTe-DSL JIT kernels)
B12X_REPO=https://github.com/local-inference-lab/b12x.git
B12X_BASE_REF=139e04048bc3bb4f7210c99e7184d8d2f0e345e7
B12X_PRS="260 267 268 269 270"

# Target GPU architecture (DGX Spark = sm_121a)
TORCH_CUDA_ARCH_LIST=12.1a