biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[v1] Add Whisper model support (encoder-decoder) (#21088)

Browse Source 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
This commit is contained in:
Russell Bryant
2025-09-10 16:53:35 -04:00
committed by GitHub
parent 4db4426404
commit 37e8182bfe
31 changed files with 429 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/models/language/generation/test_bart.py
View File

@@ -178,6 +178,7 @@ def run_test(
@pytest.mark.parametrize("max_tokens", [64])
@pytest.mark.parametrize("num_logprobs", [5])
@pytest.mark.parametrize("decoder_prompt_type", list(DecoderPromptType))
@pytest.mark.skip(reason="bart not supported in V1")
def test_models(hf_runner, vllm_runner, example_encoder_decoder_prompts, model,
dtype, max_tokens, num_logprobs, decoder_prompt_type) -> None:
@@ -201,6 +202,7 @@ def test_models(hf_runner, vllm_runner, example_encoder_decoder_prompts, model,
@pytest.mark.parametrize("max_tokens", [64])
@pytest.mark.parametrize("num_logprobs", [5])
@pytest.mark.parametrize("decoder_prompt_type", [DecoderPromptType.CUSTOM])
@pytest.mark.skip(reason="bart not supported in V1")
def test_models_distributed(hf_runner, vllm_runner,
example_encoder_decoder_prompts,
distributed_executor_backend, model, dtype,