fix: qwen3-next to use fla causal-conv1d to support packing (#3437

* fix: qwen3-next to use fla causal-conv1d to support packing

* fix: causal import and update doc for v5

* fix: hard fail for packing without fla

examples/qwen3-next/qwen3-next-80b-a3b-qlora.yaml

@@ -9,6 +9,8 @@ plugins:
 load_in_8bit: false
 load_in_4bit: true
 
+quantize_moe_experts: true
+
 datasets:
   - path: fozziethebeat/alpaca_messages_2k_test
     type: chat_template
@@ -25,7 +27,7 @@ sample_packing: true
 
 lora_r: 16
 lora_alpha: 8
-lora_dropout: 0.05
+lora_dropout: 0
 lora_target_modules:
   - linear_attn.in_proj_ba
   - linear_attn.in_proj_qkvz
@@ -34,12 +36,19 @@ lora_target_modules:
   - shared_expert.down_proj
   - shared_expert.gate_proj
   - shared_expert_gate
-  - mlp.gate
   - q_proj
   - v_proj
   - k_proj
   - o_proj
 
+# lora_target_parameters:
+#   - mlp.experts.gate_up_proj
+#   - mlp.experts.down_proj
+
+lora_mlp_kernel: false
+lora_qkv_kernel: false
+lora_o_kernel: false
+
 wandb_project:
 wandb_entity:
 wandb_watch: