# Version profile: DeepSeek-V4.1-Flash r36 (jovian-judgement, qualified 2026-09-12).
#
# The lab's FIRST published DS4.1 lock: rtx6kpro models/deepseek-v4.1-flash.md
# ("Status: qualified" for TP4/DCP1 startup, seeded sampling, text/Vision
# smoke, bounded throughput; image localinferencelab/vllm:
# jovian-judgement-community-20260912-r36 @ sha256:23ab683d...). The DS4.1
# serving profile is native DSpark K7 (weights inside the target checkpoint,
# greedy draft, standard rejection, adaptive verification), B12X
# attention/MoE/linear, 131K context, Engram ngram storage RAM/disk.
#
# The image is two-layer: the GLM entrypoint (our r35 lane) + the DS4.1
# entrypoint (serve-ds41-jovian.sh over the bundled serve-ds41-flash.sh).
# We build the same source composition here for GB10 sm_121a (the published
# image's native extension is compiled for sm_120 / CUDA 13.3 x86).
#
# Pinned by commit + tree hash (gated per repo in the Dockerfile). What moved
# over the r35 profile (r35.env):
#   vLLM  de982a50 -> 202a11a98eb (JJ b40673cd + #740 startup correction;
#         0.26.1rc0+glm53.r36.vllm202a11a9; adds the DS4.1 DSpark/Engram
#         serving path, greedy-Markov sampler fusion #738)
#   B12X  98086604 -> 323107ff (clean master; includes the DS4.1 native
#         kernels)
#   LMCache 29bc5a2e — UNCHANGED (same as r35)
#   FlashKDA 3b225bf2 + in-tree patch — UNCHANGED
#   DeepGEMM 8b1392b9 (nv_dev) — UNCHANGED (verified in the r36 tree's
#     tools/install_deepgemm.sh + cmake/external_projects/deepgemm.cmake)
#   requirements/cuda.txt (r36 tree) — torch 2.13.0, flashinfer 0.6.17:
#     SAME as our r35 GB10 pins (CUDA 13.2 aarch64 / cu130 base, documented
#     deviation from their cu133 x86 runtime).
# NEW: liburing 2.5 (apt, locks/apt-packages.txt) — io_uring reads for the
# DS4.1 Engram ngram tables in disk mode (their runtime.liburing pin).
VLLM_PIN=202a11a98eb360b73552586f2b5c5880cbd48c8c
VLLM_TREE=e20d152fa6972a4a7e624e74d198403fccb7af73
VLLM_PRETEND_VERSION=0.26.1rc0+glm53.r36.vllm202a11a9

B12X_PIN=323107ff948ca532f1f7c793b4b550c30ba5212b
B12X_TREE=18cb59ec640a5cb8d624bebfc81b919fee88340b
B12X_PRETEND_VERSION=0.1.dev0+glm53b12x.r36.323107ff

LMCACHE_PIN=29bc5a2efde737c436b04499eb62cd1776cebeec
LMCACHE_TREE=5a88a1ea9d2627c76288d056e7193f7454669b64
LMCACHE_VERSION=0.5.5.dev0+glm53checkpoints.29bc5a2e

# Same r35 behavior: empty on purpose — the r36 tree gates FlashKDA on the
# packed-checkpoint API and applies its own in-tree patch (same pin 3b225bf2
# as r35; our r27 unpatched checkout would fail the gate).
FLASH_KDA_SRC_DIR=