📝 ⚡ fix some debug output and update doc

.github/workflows/deploy.yml

@@ -4,12 +4,12 @@ on:
   push:
     branches:
       - main
-      - server_support
+      # - server_support
 
   pull_request:
     branches:
       - main
-      - server_support
+      # - server_support
 
 defaults:
   run:

doc/SUMMARY.md

@@ -7,12 +7,11 @@
 - [Injection Tutorial](en/injection_tutorial.md)
 
 # Server
-- [Server](zh/api/server/README.md)
   - [Server](en/api/server/server.md)
-  - [Website](zh/api/server/website.md)
-  - [Tabby](zh/api/server/tabby.md)
+  - [Website](en/api/server/website.md)
+  - [Tabby](en/api/server/tabby.md)
 # For Developer
-- [For Developer](en/injection_tutorial.md)
+- [Makefile Usage](en/makefile_usage.md)
 
 # FAQ
 - [FAQ](en/FAQ.md)

doc/en/V3-success.md

@@ -6,5 +6,6 @@
 ### Case 2
 - Configuration: Dual Xeon 6430 32C processors, totaling 64 cores and 128 threads, 480GB DDR5 memory, single 4090 24G graphics card
 - Performance: Running speed approximately 6-8 tokens per second 
-# NOTE
-If there are any other configurations that have been successfully run, please feel free to let us know. We will keep updating for everyone to refer to when reproducing. (It has been found that it also works on 2080, AMD, etc. (doge : ) https://docs.qq.com/smartsheet/form/AVxgQOYhhNfl%2FBB08J2%2Fv3rnnq?tab=BB08J2
+## NOTE
+If there are any other configurations that have been successfully run, please feel free to let us know. We will keep updating for everyone to refer to when reproducing. (It has been found that it also works on 2080, AMD, etc. (doge : )
\ No newline at end of file
+[click here](https://docs.qq.com/smartsheet/form/AVxgQOYhhNfl%2FBB08J2%2Fv3rnnq?tab=BB08J2)
\ No newline at end of file

doc/zh/api/server/README.md

-# Server
-Still Under Construction... (May have bugs and lack of documentation)
\ No newline at end of file

ktransformers/operators/experts.py

@@ -576,8 +576,6 @@ class KQwen2MoeSparseMoeBlock(BaseInjectedModule, Qwen2MoeSparseMoeBlock):
         routing_weights_expert = routing_weights.to(self.experts.device) if isinstance(self.experts, KExpertsBase) else routing_weights_expert.cpu()
 
         shared_expert_output = self.shared_expert(hidden_states)
-        tmp  = self.shared_expert_gate(hidden_states) 
-        print("shared_expert_gate shape ", tmp.shape)
         shared_expert_output = (
             F.sigmoid(self.shared_expert_gate(hidden_states)) * shared_expert_output
         )