Files
candle/candle-transformers
Akshay Ballal 17313a4226 Fix cuda memory error for Qwen3 non-quantized (#2987)
* Update KvCache initialization in Qwen3 model to use a fixed max position embedding value of 512

* add doc
2025-06-07 16:02:58 +02:00
..
2025-04-14 15:42:42 +02:00

candle-transformers