karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity

[Feature] Add auto-detection for reasoning_config when only reasoning_parser is set (#38214)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-04-10 01:36:26 +00:00
committed by GitHub
parent e0613702ad
commit ecbfbb8d61
10 changed files with 110 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/features/reasoning_outputs.md
+1 -1
View File
@@ -249,7 +249,7 @@ Token counting starts from `reasoning_start_str`. Once the reasoning token count
To use this feature:
- `--reasoning-parser` enables reasoning extraction.
- `--reasoning-config` defines the reasoning boundary tokens (e.g., `reasoning_start_str`, `reasoning_end_str`).
- `--reasoning-config` defines the reasoning boundary tokens (e.g., `reasoning_start_str`, `reasoning_end_str`). If not set, vLLM will attempt to automatically initialize these tokens from the reasoning parser.
- `thinking_token_budget` (a sampling parameter) sets the per-request reasoning token limit.
If `thinking_token_budget` is not specified, no explicit reasoning limit is applied beyond normal generation constraints such as `max_tokens`.