diff options
| author | Paul Buetow <paul@buetow.org> | 2026-03-18 17:28:56 +0200 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2026-03-18 17:28:56 +0200 |
| commit | bda86a3c91b307e25507e975927c3dde38f65a74 (patch) | |
| tree | 892e7d3f03a05b34528c08bd1091172c4e6de643 /snippets/hyperstack/hyperstack-vm.toml | |
| parent | d3821c76ecd18bf6256d7493596c304fff784d29 (diff) | |
Fix nemotron-super tool_call_parser; auto-clear WireGuard hostname from known_hosts
- hyperstack-vm.toml: set tool_call_parser=llama3_json for nemotron-super so vLLM
accepts tool_choice requests from opencode; model won't spontaneously call tools
so the vLLM 0.17.1 token_ids crash in llama3_json won't trigger
- hyperstack.rb: wait_for_ssh now also removes the WireGuard hostname
(hyperstack.wg1) from known_hosts alongside the IP, preventing
StrictHostKeyChecking failures across VM recreates
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'snippets/hyperstack/hyperstack-vm.toml')
| -rw-r--r-- | snippets/hyperstack/hyperstack-vm.toml | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/snippets/hyperstack/hyperstack-vm.toml b/snippets/hyperstack/hyperstack-vm.toml index f1c80a7..4ec6879 100644 --- a/snippets/hyperstack/hyperstack-vm.toml +++ b/snippets/hyperstack/hyperstack-vm.toml @@ -100,7 +100,9 @@ container_name = "vllm_nemotron_super" max_model_len = 65536 gpu_memory_utilization = 0.92 tensor_parallel_size = 1 -tool_call_parser = "" +# llama3_json lets vLLM accept tool_choice requests (required by opencode). +# Nemotron won't spontaneously call tools, so the vLLM 0.17.1 token_ids bug won't trigger. +tool_call_parser = "llama3_json" trust_remote_code = true # OpenAI GPT-OSS 20B — ultra-fast MoE (3.6B active / 20B total, MXFP4), ~14 GB on A100. |