Roland Tannous 609e3168a1 fix: serialize generation with _gen_lock to prevent concurrent queue readers ... Two overlapping /chat/completions requests could both read from the shared resp_queue, consuming and dropping each other's token events. Replace the request_id filtering (which silently dropped non-matching messages) with a threading.Lock that serializes generation — correct for single-GPU inference. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-07 04:06:51 +00:00
..
backend	fix: serialize generation with _gen_lock to prevent concurrent queue readers	2026-03-07 04:06:51 +00:00
frontend	feat: add OpenAI-compatible /v1/chat/completions endpoint	2026-03-06 07:48:09 +00:00
tests	fix: remove benchmark scripts from git tracking	2026-03-05 06:06:47 +00:00