vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-12 16:19:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

support smt and glm4

Browse source
This commit is contained in:
djw 2025-07-24 09:39:19 +00:00
parent b66d96db97
commit 613f0b7c37
8 changed files with 115 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/models/configuration_smallthinker.py
View file

@ -154,6 +154,8 @@ class SmallthinkerConfig(PretrainedConfig):
self.moe_num_primary_experts = moe_num_primary_experts
self.moe_shared_primary_experts = moe_shared_primary_experts
self.moe_ffn_hidden_size = moe_ffn_hidden_size
self.num_experts_per_tok = moe_num_active_primary_experts
self.moe_intermediate_size = moe_ffn_hidden_size
self.moe_enable_early_router = moe_enable_early_router
self.moe_primary_router_apply_softmax = moe_primary_router_apply_softmax
self.moe_num_active_primary_experts = moe_num_active_primary_experts