diff --git a/requirements/common.txt b/requirements/common.txt index 3400c24e7..2cf54e0fd 100644 --- a/requirements/common.txt +++ b/requirements/common.txt @@ -32,7 +32,7 @@ pyzmq >= 25.0.0 msgspec gguf >= 0.17.0 mistral_common[image] >= 1.8.8 -opencv-python-headless >= 4.11.0 # required for video IO +opencv-python-headless >= 4.13.0 # required for video IO pyyaml six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12 setuptools>=77.0.3,<81.0.0; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12 diff --git a/requirements/nightly_torch_test.txt b/requirements/nightly_torch_test.txt index 57770332a..589067cb8 100644 --- a/requirements/nightly_torch_test.txt +++ b/requirements/nightly_torch_test.txt @@ -25,7 +25,7 @@ transformers_stream_generator # required for qwen-vl test matplotlib # required for qwen-vl test mistral_common[image,audio] >= 1.8.8 # required for voxtral test num2words # required for smolvlm test -opencv-python-headless >= 4.11.0 # required for video test +opencv-python-headless >= 4.13.0 # required for video test datamodel_code_generator # required for minicpm3 test lm-eval[api]>=0.4.9.2 # required for model evaluation test mteb>=1.38.11, <2 # required for mteb test @@ -37,8 +37,8 @@ bitsandbytes>=0.46.1 buildkite-test-collector==0.1.9 -genai_perf==0.0.8 -tritonclient==2.51.0 +genai_perf>=0.0.8 +tritonclient>=2.51.0 numba == 0.61.2 # Required for N-gram speculative decoding numpy diff --git a/requirements/test.in b/requirements/test.in index d96d7ce32..73da100a6 100644 --- a/requirements/test.in +++ b/requirements/test.in @@ -33,7 +33,7 @@ matplotlib # required for qwen-vl test mistral_common[image,audio] >= 1.8.8 # required for voxtral test num2words # required for smolvlm test open_clip_torch==2.32.0 # Required for nemotron_vl test, Nemotron Parse in test_common.py -opencv-python-headless >= 4.11.0 # required for video test +opencv-python-headless >= 4.13.0 # required for video test datamodel_code_generator # required for minicpm3 test lm-eval[api]>=0.4.9.2 # required for model evaluation test mteb[bm25s]>=2, <3 # required for mteb test @@ -45,8 +45,8 @@ bitsandbytes==0.46.1 buildkite-test-collector==0.1.9 -genai_perf==0.0.8 -tritonclient==2.51.0 +genai_perf>=0.0.8 +tritonclient>=2.51.0 arctic-inference == 0.1.1 # Required for suffix decoding test numba == 0.61.2 # Required for N-gram speculative decoding diff --git a/requirements/test.txt b/requirements/test.txt index 79a99e68f..3dcb9918e 100644 --- a/requirements/test.txt +++ b/requirements/test.txt @@ -31,7 +31,9 @@ albumentations==1.4.6 # -r requirements/test.in # terratorch alembic==1.16.4 - # via mlflow + # via + # mlflow + # optuna annotated-doc==0.0.4 # via fastapi annotated-types==0.7.0 @@ -145,6 +147,8 @@ colorama==0.4.6 # tqdm-multiprocess colorful==0.5.6 # via ray +colorlog==6.10.1 + # via optuna contourpy==1.3.0 # via matplotlib coverage==7.10.6 @@ -252,7 +256,7 @@ fsspec==2024.9.0 # torch ftfy==6.3.1 # via open-clip-torch -genai-perf==0.0.8 +genai-perf==0.0.16 # via -r requirements/test.in genson==1.3.0 # via datamodel-code-generator @@ -389,6 +393,7 @@ jinja2==3.1.6 # via # datamodel-code-generator # flask + # genai-perf # mlflow # torch jiwer==3.0.5 @@ -528,7 +533,7 @@ numba==0.61.2 # librosa numexpr==2.10.1 # via lm-eval -numpy==1.26.4 +numpy==2.2.6 # via # -r requirements/test.in # accelerate @@ -558,6 +563,7 @@ numpy==1.26.4 # numba # numexpr # opencv-python-headless + # optuna # pandas # patsy # peft @@ -637,7 +643,7 @@ opencensus==0.11.4 # via ray opencensus-context==0.1.3 # via opencensus -opencv-python-headless==4.11.0.86 +opencv-python-headless==4.13.0.90 # via # -r requirements/test.in # albucore @@ -660,6 +666,10 @@ opentelemetry-sdk==1.35.0 # ray opentelemetry-semantic-conventions==0.56b0 # via opentelemetry-sdk +optuna==3.6.1 + # via genai-perf +orjson==3.11.5 + # via genai-perf packaging==24.2 # via # accelerate @@ -678,6 +688,7 @@ packaging==24.2 # lightning-utilities # matplotlib # mlflow-skinny + # optuna # peft # plotly # pooch @@ -717,6 +728,8 @@ peft==0.16.0 # lm-eval perceptron==0.1.4 # via -r requirements/test.in +perf-analyzer==0.1.0 + # via genai-perf pillow==10.4.0 # via # genai-perf @@ -903,6 +916,7 @@ pyyaml==6.0.2 # lightning # mlflow-skinny # omegaconf + # optuna # peft # pytorch-lightning # ray @@ -1065,6 +1079,7 @@ sortedcontainers==2.4.0 soundfile==0.12.1 # via # -r requirements/test.in + # genai-perf # librosa # mistral-common soxr==0.5.0.post1 @@ -1075,6 +1090,7 @@ sqlalchemy==2.0.41 # via # alembic # mlflow + # optuna sqlitedict==2.1.0 # via lm-eval sqlparse==0.5.3 @@ -1204,6 +1220,7 @@ tqdm==4.66.6 # mteb # nltk # open-clip-torch + # optuna # peft # pqdm # pretrainedmodels @@ -1226,10 +1243,8 @@ transformers-stream-generator==0.0.5 # via -r requirements/test.in triton==3.5.1 # via torch -tritonclient==2.51.0 - # via - # -r requirements/test.in - # genai-perf +tritonclient==2.64.0 + # via -r requirements/test.in typepy==1.3.2 # via # dataproperty diff --git a/tests/entrypoints/openai/test_translation_validation.py b/tests/entrypoints/openai/test_translation_validation.py index cae45872e..23502ea1b 100644 --- a/tests/entrypoints/openai/test_translation_validation.py +++ b/tests/entrypoints/openai/test_translation_validation.py @@ -267,12 +267,16 @@ async def test_audio_with_max_tokens(mary_had_lamb, client_and_model): out_tokens = tok(out_text, add_special_tokens=False)["input_ids"] assert len(out_tokens) == 1 # max_completion_tokens > max_model_len + # max_model_len=32768 for Gemma-3n-E2B-it transcription = await client.audio.transcriptions.create( model=model_name, file=mary_had_lamb, response_format="text", temperature=0.0, - extra_body={"max_completion_tokens": int(1e6)}, + extra_body={ + "max_completion_tokens": int(1e6), + "repetition_penalty": 1.3, + }, ) out = json.loads(transcription) out_text = out["text"]