From 792b44f2ed9668cce7f267ff0ae4950ed9b4a5de Mon Sep 17 00:00:00 2001 From: ExtReMLapin <3909752+ExtReMLapin@users.noreply.github.com> Date: Fri, 29 Aug 2025 19:25:40 +0200 Subject: [PATCH] server : add documentation for `parallel_tool_calls` param (#15647) Co-authored-by: Pierre F --- docs/function-calling.md | 2 ++ tools/server/README.md | 2 ++ 2 files changed, 4 insertions(+) diff --git a/docs/function-calling.md b/docs/function-calling.md index 37eacaf310..67cf785c7a 100644 --- a/docs/function-calling.md +++ b/docs/function-calling.md @@ -21,6 +21,8 @@ Function calling is supported for all models (see https://github.com/ggml-org/ll - Use `--chat-template-file` to override the template when appropriate (see examples below) - Generic support may consume more tokens and be less efficient than a model's native format. +- Multiple/parallel tool calling is supported on some models but disabled by default, enable it by passing `"parallel_tool_calls": true` in the completion endpoint payload. +
Show some common templates and which format handler they use diff --git a/tools/server/README.md b/tools/server/README.md index baf3730add..6962b0d3a2 100644 --- a/tools/server/README.md +++ b/tools/server/README.md @@ -1143,6 +1143,8 @@ The `response_format` parameter supports both plain JSON output (e.g. `{"type": `parse_tool_calls`: Whether to parse the generated tool call. +`parallel_tool_calls` : Whether to enable parallel/multiple tool calls (only supported on some models, verification is based on jinja template). + *Examples:* You can use either Python `openai` library with appropriate checkpoints: