Skip to content

[Model] Add Ernie-4.5 #637

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jul 1, 2025
Merged

[Model] Add Ernie-4.5 #637

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
27a4dba
update: ernie45 exmaple on a800
Corle-hyz Jun 30, 2025
210bd09
update: ernie45 modeling for vllm
Corle-hyz Jun 30, 2025
404ddb4
update: ernie45 modeling for vllm
Corle-hyz Jun 30, 2025
59cf83a
typo: ernie34 -> ernie45
Corle-hyz Jul 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions examples/ernie45/conf/serve.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
defaults:
- _self_
- serve: 300b

experiment:
exp_name: ernie45_300b
exp_dir: outputs/${experiment.exp_name}
task:
type: serve
runner:
hostfile: null
deploy:
use_fs_serve: false
envs:
CUDA_VISIBLE_DEVICES: 0,1,2,3,4,5,6,7
CUDA_DEVICE_MAX_CONNECTIONS: 1

action: run

hydra:
run:
dir: ${experiment.exp_dir}/hydra
24 changes: 24 additions & 0 deletions examples/ernie45/conf/serve/300b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
- serve_id: vllm_model
engine: vllm
engine_args:
model: /nfs/hcr/models/PaddlePaddle/ERNIE-4.5-300B-A47B-Base-PT
host: 0.0.0.0
max_model_len: 256
max_num_seqs: 1
uvicorn_log_level: warning
port: 30000
engine_args_specific:
vllm:
tensor_parallel_size: 8
pipeline_parallel_size: 1
gpu_memory_utilization: 0.98
trust_remote_code: true
# GMEM not enough if disable eager mode
enforce_eager: true
# enable_chunked_prefill: true
profile:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

auto-tuner has been verified?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not yet

prefix_len: 0
input_len: 1024
output_len: 1024
num_prompts: 128
range_ratio: 1
Loading
Loading