diff options
| author | Paul Buetow <paul@buetow.org> | 2026-03-21 10:49:35 +0200 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2026-03-21 10:49:35 +0200 |
| commit | ea0f9f7f51b32f0c392f75aa0cc3231211f54757 (patch) | |
| tree | 378d01dbc87dc0ef9f4fbd6ec7788e0a62f66876 /hyperstack-vm1.toml | |
| parent | 4baa087445a11b856139f55adab262fa97384033 (diff) | |
Remove LiteLLM and Claude Code repo references (task 301)
Diffstat (limited to 'hyperstack-vm1.toml')
| -rw-r--r-- | hyperstack-vm1.toml | 12 |
1 files changed, 1 insertions, 11 deletions
diff --git a/hyperstack-vm1.toml b/hyperstack-vm1.toml index 1b116bd..6109472 100644 --- a/hyperstack-vm1.toml +++ b/hyperstack-vm1.toml @@ -41,8 +41,6 @@ allowed_ssh_cidrs = ["auto"] allowed_wireguard_cidrs = ["auto"] # Port 11434 is shared by both Ollama and vLLM for firewall compatibility. ollama_port = 11434 -# Port 4000: LiteLLM Anthropic-API proxy (used with vLLM). -litellm_port = 4000 [bootstrap] enable_guest_bootstrap = true @@ -60,7 +58,7 @@ num_parallel = 1 context_length = 32768 pull_models = ["nemotron-3-super"] -# vLLM serves one model via Docker; LiteLLM translates Anthropic API → OpenAI. +# vLLM serves one model via Docker on the OpenAI-compatible API. # VM1 defaults to nemotron-3-super; use 'model switch' to load any other preset. [vllm] install = true @@ -75,14 +73,6 @@ tensor_parallel_size = 1 tool_call_parser = "qwen3_xml" trust_remote_code = true extra_vllm_args = ["--reasoning-parser", "nemotron_v3"] -# LiteLLM maps each entry to the vLLM model; add new Anthropic model IDs here. -litellm_master_key = "sk-litellm-master" -litellm_claude_model_names = [ - "claude-sonnet-4-20250514", - "claude-opus-4-20250514", - "claude-opus-4-6-20260604", - "claude-haiku-3-5-20241022" -] # Named model presets for 'ruby hyperstack.rb --config hyperstack-vm1.toml model switch <name>'. # Each preset overrides the matching [vllm] field; unset fields fall back to [vllm] defaults. |