609e3168a1
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> |
||
|---|---|---|
| .. | ||
| assets | ||
| auth | ||
| core | ||
| loggers | ||
| models | ||
| requirements | ||
| routes | ||
| state | ||
| tests | ||
| utils | ||
| colab.py | ||
| main.py | ||
| run.py | ||