Skip to content

model: support OpenAI Whisper #8064

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

Closed
MahmoudAshraf97 wants to merge 18 commits into from
Closed

model: support OpenAI Whisper #8064

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
878d33f
initial commit
MahmoudAshraf97 Jul 15, 2025
3a6e4e4
fix data loading
MahmoudAshraf97 Jul 23, 2025
9177f4d
working prefill
MahmoudAshraf97 Jul 24, 2025
0867860
reimplement using SGL modules
MahmoudAshraf97 Jul 24, 2025
bdec36d
pad_input_ids
MahmoudAshraf97 Jul 25, 2025
cfd87e2
use vocabparallelembedding
MahmoudAshraf97 Jul 25, 2025
79c1a40
disable kvcache for the encoder
MahmoudAshraf97 Jul 25, 2025
b852ffd
change lm head class
MahmoudAshraf97 Jul 25, 2025
22e15ab
fix output signature
MahmoudAshraf97 Jul 28, 2025
9bc44c0
correct permutations for hidden state
MahmoudAshraf97 Jul 28, 2025
0cea116
use correct processor output shapes
MahmoudAshraf97 Jul 28, 2025
981389f
set as enc-dec model
MahmoudAshraf97 Jul 28, 2025
258eda0
use encoder position ids and encoder lengths
MahmoudAshraf97 Jul 28, 2025
061886c
update processor init
MahmoudAshraf97 Jul 29, 2025
6392558
fix `proj_out` weight
MahmoudAshraf97 Jul 31, 2025
a816ea1
update processor to accept input ids
MahmoudAshraf97 Aug 1, 2025
569ae68
Merge branch 'main' into whisper
JustinTong0323 Jan 9, 2026
97b7629
Merge branch 'main' into whisper
JustinTong0323 Jan 12, 2026
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
12 changes: 10 additions & 2 deletions python/sglang/srt/configs/model_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1078,6 +1078,7 @@ def is_generation_model(model_architectures: List[str], is_embedding: bool = Fal
"InternVLChatModel",
"InternS1ForConditionalGeneration",
"Phi4MMForCausalLM",
"WhisperForConditionalGeneration",
"Step3VLForConditionalGeneration",
"POINTSV15ChatModel",
"DotsVLMForCausalLM",
Expand Down Expand Up @@ -1114,11 +1115,18 @@ def is_image_gen_model(model_architectures: List[str]):


def is_audio_model(model_architectures: List[str]):
return False
models = [
"WhisperForConditionalGeneration",
]
return any(model in model_architectures for model in models)


def is_encoder_decoder_model(model_architectures: List[str]):
return "MllamaForConditionalGeneration" in model_architectures
models = [
"MllamaForConditionalGeneration",
"WhisperForConditionalGeneration",
]
return any(model in model_architectures for model in models)


def is_local_attention_model(model_architectures: List[str]):
Expand Down
Loading
Loading