rob thijssen
c85d50066e
- cortex.spec: gateway binary, cortex.service systemd unit, cortex.toml + models.toml config files - neuron.spec: neuron binary, neuron.service systemd unit, neuron.toml config file - Parallel CI: srpm-cortex and srpm-neuron jobs build SRPMs concurrently, then publish to separate COPR repos (helexa/cortex and helexa/neuron) - Shared cortex user/group across both packages - Example configs: cortex.example.toml, neuron.example.toml, models.example.toml Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
30 lines
655 B
TOML
30 lines
655 B
TOML
# models.example.toml — model catalogue
|
|
#
|
|
# Copy to /etc/cortex/models.toml and adjust for your environment.
|
|
# Describes how to serve each model. Cortex matches these profiles
|
|
# against discovered neuron topologies for placement decisions.
|
|
|
|
[[models]]
|
|
id = "your-org/large-model"
|
|
harness = "mistralrs"
|
|
quant = "Q4_K_M"
|
|
vram_mb = 19000
|
|
min_devices = 2
|
|
min_device_vram_mb = 10000
|
|
pinned_on = ["gpu-large"]
|
|
|
|
[[models]]
|
|
id = "your-org/medium-model"
|
|
harness = "mistralrs"
|
|
quant = "Q6_K"
|
|
vram_mb = 12000
|
|
min_devices = 1
|
|
pinned_on = ["gpu-medium"]
|
|
|
|
[[models]]
|
|
id = "your-org/embedding-model"
|
|
harness = "mistralrs"
|
|
quant = "Q8_0"
|
|
vram_mb = 8000
|
|
min_devices = 1
|