Closed littletomatodonkey closed 3 months ago
Please refer to the CogVLM:
All position ids in cogvlm are fixed, and actually in TRT-LLM cogvlm realization, position_ids is a dead input tensor for gpt_attention, do you know which case can be refered for input position_ids? Thanks!
i solved it by realizing ROPE myself after qkv calculation and set rope_embedding_type as None in gpt_attention_plugin.
@littletomatodonkey please share your code. also running into the same issue.
You can refer to chatglm model build process. There are 3 steps
I use python runtime in TRT-LLM 071 as in newer version, it's hard to hack code in the gptmanager.
Hi, in my model, some of the position ids are same(which are all vision tokens). For example, for an input with seq_length as 5, 1~3 ids are vision tokens. The common position ids are
But for me, i want to set it as follows. (All the vision tokens are same)
Is there any reference in TRT-LLM to finish it with gpt_attention_plugin? Thanks!