docs: document the opt-in exact-match LLM response cache - #405

Merged

rapids-bot[bot] merged 11 commits into

NVIDIA:mainfrom

zhongxuanwang-nv:docs/response-cache-stage1

Jul 31, 2026

Commits on Jul 14, 2026

docs: document the opt-in response cache
zhongxuanwang-nv
committed
47df001

Commits on Jul 21, 2026

Merge upstream/main into docs/response-cache-stage1
zhongxuanwang-nv
committed
d19ca69

Commits on Jul 23, 2026

Merge upstream/main into docs/response-cache-stage1
zhongxuanwang-nv
committed
1681d30
docs(node): use response-cache camelCase API
zhongxuanwang-nv
committed
00ded9b
docs(response-cache): qualify reuse claims
zhongxuanwang-nv
committed
d0fae8e

Commits on Jul 27, 2026

docs(response-cache): correct configuration guidance
zhongxuanwang-nv
committed
0a38720

Commits on Jul 30, 2026

Merge upstream/main into docs/response-cache-stage1
zhongxuanwang-nv
committed
4332c27

Commits on Jul 31, 2026