diff options
| author | Paul Buetow <paul@buetow.org> | 2026-03-21 12:58:08 +0200 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2026-03-21 12:58:08 +0200 |
| commit | 437168c7a47ee656edc91177b9753957b9361209 (patch) | |
| tree | 0b0b1fb74137c0dd6f2bb4a9a4e7b67f33ea7129 /hyperstack-vm.toml | |
| parent | f9a2ffcdf1d7dd9612c2d328585f58310236bd9b (diff) | |
Set single-VM default to GPT-OSS 120B; add hyperstack Pi provider and fish abbr
- hyperstack-vm.toml: switch [vllm] default from Qwen3-Coder-Next to
openai/gpt-oss-120b (container_name, max_model_len=131072,
tool_call_parser=''); labels already reflected gpt-oss-120b
- pi/agent/models.json: add 'hyperstack' provider pointing at
hyperstack.wg1:11434/v1 with GPT-OSS 120B as primary model and all
preset models registered (alongside hyperstack1/hyperstack2)
- hyperstack.fish: add pi-hyperstack abbreviation for single-VM GPT-OSS 120B
- README.md: update fish abbreviations table, provider table, VM config
table, and Single-VM setup section to reflect the new defaults
Diffstat (limited to 'hyperstack-vm.toml')
| -rw-r--r-- | hyperstack-vm.toml | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/hyperstack-vm.toml b/hyperstack-vm.toml index 28de975..88f2a19 100644 --- a/hyperstack-vm.toml +++ b/hyperstack-vm.toml @@ -58,14 +58,17 @@ pull_models = ["qwen3-coder-next", "qwen3-coder:30b", "gpt-oss:20b", "gpt-oss:12 # Use --vllm / --no-vllm CLI flags to override install at runtime. [vllm] install = true -model = "bullpoint/Qwen3-Coder-Next-AWQ-4bit" +model = "openai/gpt-oss-120b" # HuggingFace model cache on ephemeral NVMe (fast; survives reboots on most providers). hug_cache_dir = "/ephemeral/hug" -container_name = "vllm_qwen3" -max_model_len = 262144 +container_name = "vllm_gpt_oss_120b" +# Hard architecture limit: max_position_embeddings=131072 in model config.json. +max_model_len = 131072 gpu_memory_utilization = 0.92 tensor_parallel_size = 1 -tool_call_parser = "qwen3_coder" +# tool_call_parser="" disables --enable-auto-tool-choice; the llama3_json parser crashes +# on gpt-oss responses (vLLM 0.17.1 adds token_ids to responses, breaking the parser API). +tool_call_parser = "" # Named model presets for 'ruby hyperstack.rb model switch <name>'. # Each preset overrides the matching [vllm] field; unset fields fall back to [vllm] defaults. |