Guides

Task-oriented documentation: how to measure PocketLLM, how to call it, and how to release it. Start with Benchmarking and reporting rules before quoting any performance number from this site — it defines the measurement conventions the rest of the documentation assumes.

Guide	What it covers
Benchmarking and reporting rules	The prefill/decode split, what every result record must contain, and the hardware and invocation details a comparable number needs.
PocketLLM API and backend guide	The single user-facing API over the two execution planes (Torch and C++), backend selection, tensor parallelism, and the batch/scheduler surface.
PyPI release guide	The single source of truth for releasing pocketllm to PyPI, including the Test PyPI dry run.
Ascend SoC generations	Why 910B and 910B1–910B4 are different chips, how to read Short_SoC_version, and why they cannot share kernels.

For install and build instructions, see Getting started. For per-model runtimes see Model guides.