# The GB10's display carveout as KV cache. The firmware reserves 2 GiB for a
# display that the driver never uses on this chip. kindling-spark-os
# (github.com/kindlingai/kindling-spark-os) runs dispramd, which lends that
# range to CUDA processes. This file mounts dispramd's socket and the host's
# copy of its vLLM plugin, so the client always matches the daemon. The plugin
# adds what dispramd can lend (1.99 GiB) to the pinned KV pool and maps the
# pool's tail onto it.
#
# kindling-spark-os's 64 KiB kernel also returns ~2 GiB of RAM, so at TP=4
# this raises the pinned pool by 2 GiB (KV_EXTRA_MEMORY). TP=2 has no room for
# it, and TP=3 and 6 are unmeasured.
#
# ./glm53 adds this file by itself when /run/dispram/dispram.sock exists.
# DISPRAM=0 leaves it out. Every rank should have it: vLLM sizes the pool by
# the smallest rank, so one box without dispramd cancels the gain.
services:
  glm53:
    volumes:
      - /run/dispram:/run/dispram
      - /opt/kindling/dispram/python:/opt/dispram:ro
    environment:
      - PYTHONPATH=/opt/dispram
      - KV_EXTRA_MEMORY=${KV_EXTRA_MEMORY:-2147483648}