You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
ronnywang 87e4c4fa87
[NPU] support npu llama2-13B export & inference (#8442)
5 hours ago
..
baichuan [DOC] Add pretraining docs and report pretrain performance. (#7437) 5 months ago
bloom llm doc update (#7478) 5 months ago
chatglm llm doc update (#7478) 5 months ago
chatglm2 llm doc update (#7478) 5 months ago
docs [Bug Fix]Fix merge parameters in pp (#8239) 1 month ago
ernie-3.5-se use tensor.shape bug not paddle.shape(tensor) (#8260) 1 month ago
gemma [LLM]Support Gemma model (#8082) 1 month ago
glm remove load state as np. (#7120) 7 months ago
gpt-3 [AutoParallel] support GPT for auto_parallel (#8160) 1 month ago
llama [NPU] support npu llama2-13B export & inference (#8442) 5 hours ago
mixtral [Mixtral] Add mixtral moe (#7803) 2 months ago
opt llm doc update (#7478) 5 months ago
qwen Pissa (#8250) 1 month ago
tests [DOC] Add pretraining docs and report pretrain performance. (#7437) 5 months ago
.gitignore [LLM] Support ptq inference (#7224) 6 months ago
README.md Update llm docs requirements (#8336) 2 weeks ago
argument.py Pissa (#8250) 1 month ago
benchmark.sh [LLM] Support block_attention/cachekv quant for llama (#7649) 4 months ago
data.py [Tokenizer]Add Chat template (#8226) 3 weeks ago
export_model.py [NPU] support npu llama2-13B export & inference (#8442) 5 hours ago
finetune_generation.py fix npu sft ckpt load bug and no FA bug (#8438) 5 days ago
flask_server.py fix br gradio (#7788) 4 months ago
fused_layers.py add qwen benchmark (#7758) 3 months ago
gradio_ui.py fix (#7992) 2 months ago
merge_lora_params.py [llm]support lora merge (#7733) 4 months ago
merge_tp_and_pp_params.py [Bug Fix]Fix merge parameters in pp (#8239) 1 month ago
predictor.py [NPU] support npu llama2-13B export & inference (#8442) 5 hours ago
quant.py Support AWQ & GroupWiseQuant for LLMs (#7688) 4 months ago
request_flask_server.py [New Features] support dynamic src_length (#7740) 4 months ago
run_pretrain.py [XPU] llama add xpu support (#8282) 3 weeks ago
utils.py [LLM] relocate tensor_parallel_output to avoid conflict (#8419) 1 week ago