diff options
| author | Paul Buetow <paul@buetow.org> | 2026-03-18 17:42:00 +0200 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2026-03-18 17:42:00 +0200 |
| commit | a7d3d2d4339815cf4a39b58873069b07a0ac1d47 (patch) | |
| tree | a8271bd320e846965b36fd8d430b4da3130d422d /snippets/hyperstack/hyperstack.rb | |
| parent | bda86a3c91b307e25507e975927c3dde38f65a74 (diff) | |
nemotron-super: revert to no tool calling; add nemotron_v3 reasoning parser
vLLM 0.17.1 has no tool call parser for Nemotron's custom XML format
(<tool_call><function=...><parameter=...>). Setting llama3_json produced
garbage output. Reverted to tool_call_parser="" with a clear comment.
Added --reasoning-parser nemotron_v3 via extra_vllm_args so <think> tokens
are properly exposed as reasoning_content in the API response.
For agentic work requiring tool calls, switch to qwen3-coder-next or devstral.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'snippets/hyperstack/hyperstack.rb')
0 files changed, 0 insertions, 0 deletions