Pull requests / #1004
#1004 serve: /props total_slots is the engine's batch slots
closed · @midagedev · 0 comentários · No GitHub
Descrição
`/props` always reports `total_slots: 1`. With `"parallel": 3` the engine runs three batch slots, and `/v1/status` reports `concurrency.serving: 3`. Clients that read `total_slots` think the server runs one request at a time. toktape refused a 3-session run for this reason. The fix reports the engine's batch slots in `/props`, with the same expression as `/v1/status` (at least 1). Evidence: - RTX 3090 with `"parallel": 3`: the engine log says `--batch: 3 slot sessions`, but `/props` said `total_slots: 1`. - New test `test_props_total_slots_follows_the_batch_slots`: fails before the fix (`1 != 3`) and passes after. All 140 tests in `serve/test_server.py` pass. `/slots` still lists one slot. Open PR #562 changes that block, so I left it alone. I wrote this with an AI coding assistant and checked the change and the test runs myself.
No site
Links install, modelos, releases.