Skip to content
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

[ci] convert nxdi tests to aot compiled #2700

Merged
merged 1 commit into from
Feb 2, 2025
Merged

[ci] convert nxdi tests to aot compiled #2700

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 10 additions & 4 deletions tests/integration/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -902,15 +902,21 @@ def test_llama_speculative_compiled(self):
"transformers_neuronx_rolling_batch llama-speculative-compiled-rb"
.split())

def test_llama_vllm_nxdi(self):
def test_llama_8b_vllm_nxdi(self):
# For neuron, handler is names as transformers_neuronx, but this handler supports, TNX, NXDI and optimum.
with Runner('pytorch-inf2', 'llama-3-1-8b-instruct-vllm-nxdi') as r:
prepare.build_transformers_neuronx_handler_model(
"llama-3-1-8b-instruct-vllm-nxdi")
r.launch(container='pytorch-inf2-4')
r.launch(
container="pytorch-inf2-4",
cmd=
"partition --model-dir /opt/ml/input/data/training --save-mp-checkpoint-path /opt/ml/input/data/training/aot --skip-copy"
)
r.launch(container="pytorch-inf2-4",
cmd="serve -m test=file:/opt/ml/model/test/aot")
client.run(
"transformers_neuronx_rolling_batch llama-3-1-8b-instruct-vllm-nxdi"
)
.split())

def test_llama_vllm_nxdi_aot(self):
with Runner('pytorch-inf2',
Expand All @@ -926,7 +932,7 @@ def test_llama_vllm_nxdi_aot(self):
cmd="serve -m test=file:/opt/ml/model/test/aot")
client.run(
"transformers_neuronx_rolling_batch llama-3-2-1b-instruct-vllm-nxdi-aot"
)
.split())


@pytest.mark.correctness
Expand Down
Loading