mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-04-28 03:30:40 +00:00
1e8bc031cc
* feat(core): adaptive output token escalation (8K default + 64K retry) 99% of model responses are under 5K tokens, but we previously reserved 32K for every request. This wastes GPU slot capacity by ~4x. Now the default output limit is 8K. When a response hits this cap (stop_reason=max_tokens), it automatically retries once at 64K — only the ~1% of requests that actually need more tokens pay the cost. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: add design doc and user doc for adaptive output token escalation - Add design doc covering problem, architecture, token limit determination, escalation mechanism, and design decisions - Document QWEN_CODE_MAX_OUTPUT_TOKENS env var in settings.md - Add max_tokens adaptive behavior explanation in model config section --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| channels | ||
| cli | ||
| core | ||
| sdk-java | ||
| sdk-typescript | ||
| test-utils | ||
| vscode-ide-companion | ||
| web-templates | ||
| webui | ||
| zed-extension | ||