Commit Graph

2 Commits

Author SHA1 Message Date
485ddf2996 Fixed Quantized Qwen3 Model (#2951)
* optimize KV cache to reduce GPU memory usage

* revert to using candle_nn::kv_cache::KvCache with initial capacity of 512
2025-05-13 05:53:42 +02:00
3d05f5cf3d Qwen3 quantized implementation (#2939)
* fixed quantized_phi3 implementation

* quantized_qwen3 implementation

* Update quantized_phi3.rs

* Update quantized_phi3.rs

* add quantized_qwen3 example

* Clippy fixes.

* Cleanup.

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>
2025-05-08 15:06:10 +02:00