mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
90b226db29
* We can have a tokenizer anywhere. * Handling potential lack of offsets (python tokenizer) * Remove redundancy. * Fixing the tests. * Flake.lock update ? * Fixing the GIL locking. * Fixing mamba by using the transformers version. * Adding the legacy handle. * Ellide lifetime. * Lint. * Deprecation message. * Fixing bad rebase.
70 lines
2.0 KiB
Python
70 lines
2.0 KiB
Python
import pytest
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def fused_kernel_mamba_handle(launcher):
|
|
with launcher("state-spaces/mamba-130m-hf", num_shard=1) as handle:
|
|
yield handle
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
async def fused_kernel_mamba(fused_kernel_mamba_handle):
|
|
await fused_kernel_mamba_handle.health(300)
|
|
return fused_kernel_mamba_handle.client
|
|
|
|
|
|
@pytest.mark.release
|
|
@pytest.mark.asyncio
|
|
async def test_mamba(fused_kernel_mamba, response_snapshot):
|
|
response = await fused_kernel_mamba.generate(
|
|
"What is Deep Learning?", max_new_tokens=10
|
|
)
|
|
|
|
assert response.details.generated_tokens == 10
|
|
assert response.generated_text == "\n\nDeep learning is a new type of machine"
|
|
assert response == response_snapshot
|
|
|
|
|
|
@pytest.mark.release
|
|
@pytest.mark.asyncio
|
|
async def test_mamba_all_params(fused_kernel_mamba, response_snapshot):
|
|
response = await fused_kernel_mamba.generate(
|
|
"blue, red, yellow, ",
|
|
max_new_tokens=10,
|
|
repetition_penalty=1.2,
|
|
return_full_text=True,
|
|
stop_sequences=["test"],
|
|
temperature=0.5,
|
|
top_p=0.9,
|
|
top_k=10,
|
|
truncate=5,
|
|
typical_p=0.9,
|
|
watermark=True,
|
|
decoder_input_details=True,
|
|
seed=0,
|
|
)
|
|
|
|
assert response.details.generated_tokens == 10
|
|
assert (
|
|
response.generated_text
|
|
== "blue, red, yellow, \nand blue colors. A number of different color"
|
|
)
|
|
assert response == response_snapshot
|
|
|
|
|
|
@pytest.mark.release
|
|
@pytest.mark.asyncio
|
|
async def test_mamba_load(
|
|
fused_kernel_mamba, generate_load, generous_response_snapshot
|
|
):
|
|
responses = await generate_load(
|
|
fused_kernel_mamba, "What is Deep Learning?", max_new_tokens=10, n=4
|
|
)
|
|
|
|
assert len(responses) == 4
|
|
assert responses[0].generated_text == "\n\nDeep learning is a new type of machine"
|
|
assert all([r.generated_text == responses[0].generated_text for r in responses])
|
|
assert responses[0].generated_text == "\n\nDeep learning is a new type of machine"
|
|
|
|
assert responses == generous_response_snapshot
|