scott bdde4a2480 Add startup warmup and make fp16 autocast fault-tolerant ...

Warmup: run a synthesis before accepting Wyoming connections so MIOpen
benchmarks and caches all conv layer shapes. Without this, the first HA
request triggers hundreds of benchmark runs and times out.

fp16: wrap in try/except so a failed autocast retries in fp32 rather
than dropping the request silently.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-05 13:48:41 -04:00

1.8 KiB

Raw Blame History

View Raw