mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
A restricted policy hides the interpreters a model-run command needs, so its first import fails. `--agent` and `--enable-code-execution` now pick a developer profile that opens the toolchain roots; everything else stays restricted, and explicit flags still win. The CPU rlimit could fire before the execution timeout reported anything. It is now raised to cover the timeout wherever rlimits apply, and code execution defaults to 60s. The example config documents the profile, and a test loads it, since nothing did. Co-authored-by: Hanzo Dev <[email protected]>
46 lines
1.0 KiB
TOML
46 lines
1.0 KiB
TOML
command = "serve"
|
|
|
|
[server]
|
|
host = "0.0.0.0"
|
|
port = 1234
|
|
|
|
[runtime]
|
|
max_seqs = 32
|
|
enable_search = true
|
|
search_embedding_model = "embedding-gemma"
|
|
# code_exec_permission = "auto" # "auto" | "ask" | "deny"
|
|
|
|
[paged_attn]
|
|
mode = "auto"
|
|
|
|
# OS-level sandbox applied to model-generated code execution.
|
|
# mode = "auto"|"on"|"off" (auto = on for Linux/macOS, no-op elsewhere)
|
|
# profile = "developer"|"restricted" (developer is the default once agent or code tools are on)
|
|
# network defaults to "full" for developer and "loopback" for restricted.
|
|
# Limits and network override the profile defaults when set.
|
|
[sandbox]
|
|
mode = "auto"
|
|
profile = "developer"
|
|
max_memory_mb = 2048
|
|
max_cpu_secs = 600
|
|
max_procs = 64
|
|
# network = "loopback" # "none" | "loopback" | "full"
|
|
|
|
[[models]]
|
|
kind = "auto"
|
|
model_id = "meta-llama/Llama-3.2-3B-Instruct"
|
|
|
|
[models.quantization]
|
|
in_situ_quant = "4"
|
|
|
|
[[models]]
|
|
kind = "multimodal"
|
|
model_id = "Qwen/Qwen2-VL-2B-Instruct"
|
|
|
|
[models.multimodal]
|
|
max_num_images = 4
|
|
|
|
[[models]]
|
|
kind = "embedding"
|
|
model_id = "google/embeddinggemma-300m"
|