vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-16 01:59:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

support smt and qlm4

Browse source
This commit is contained in:
djw 2025-07-25 12:48:51 +00:00
parent 712ad1fa3c
commit 48bc6185b5
9 changed files with 65 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ktransformers/models/modeling_glm4_moe.py
View file

@ -625,7 +625,7 @@ class Glm4MoeForCausalLM(Glm4MoePreTrainedModel, GenerationMixin):
inputs_embeds=inputs_embeds,
use_cache=use_cache,
cache_position=cache_position,
**kwargs,
# **kwargs,
)
hidden_states = outputs.last_hidden_state
@ -635,7 +635,7 @@ class Glm4MoeForCausalLM(Glm4MoePreTrainedModel, GenerationMixin):
loss = None
if labels is not None:
loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)
loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size)
return CausalLMOutputWithPast(
loss=loss,