File test_server_prefix_cache.py

server/scripts/test_server_prefix_cache.py:None–None · view source on GitHub ↗

Source from the content-addressed store, hash-verified

1	"""End-to-end Phase A test: prefix cache integration.
2
3	Sends 3 chat completions sharing a 2K-token system prompt, asserts turns 2/3
4	have noticeably faster prefill than turn 1.

nothing calls this directly

mainFunction · 0.70

no test coverage detected