Add Quantized gemma3 and qwen3 (#87)

* add min_all and max_all to tensor

* add quantized gemma 3 and qwen3

* add files to mod

---------

Co-authored-by: mp <pro@macbookpro>

Author: AlpineVibrations

candle-transformers/src/models/mod.rs

@@ -56,6 +56,7 @@ pub mod phi3;
 pub mod pixtral;
 pub mod quantized_blip;
 pub mod quantized_blip_text;
+pub mod quantized_gemma3;
 pub mod quantized_llama;
 pub mod quantized_llama2_c;
 pub mod quantized_metavoice;
@@ -65,6 +66,7 @@ pub mod quantized_moondream;
 pub mod quantized_mpt;
 pub mod quantized_phi;
 pub mod quantized_qwen2;
+pub mod quantized_qwen3;
 pub mod quantized_recurrent_gemma;
 pub mod quantized_rwkv_v5;
 pub mod quantized_rwkv_v6;