Closed jjjjohnson closed 4 months ago
We have not support s-lora TP on ALL model since that different model have different qkv linear projection. If you can provide the adapter, we might be able to add the support you need.
Hi @grimoire Can you show which model type currently support s-lora TP? I will try to solve the issue and PR.
Qwen14b chat:
Qwen14b chat with lora:
And qwen.py mod.register_parameter(name, dist_param)
is not able to deal with nested c_attn
All models with seprated q,k,v proj support tp. chatglm2 has similar pattern like qwen
Thanks @grimoire Qwen has a combined q,k,v proj called c_attn
, Looks like Baichuan is also very similar to Qwen.
Checklist
Describe the bug
Looks like in Pytorch backend Slora and TP cannot be turned on at the same time...
Reproduction
Environment
Error traceback
No response