Refactor STT runtime around model-owned adapters#173
Merged
ericcurtin merged 7 commits intovllm-project:mainfrom Mar 19, 2026
Merged
Refactor STT runtime around model-owned adapters#173ericcurtin merged 7 commits intovllm-project:mainfrom
ericcurtin merged 7 commits intovllm-project:mainfrom
Conversation
Move `STTExecutor` out of `vllm_metal/v1/model_runner.py` into `vllm_metal/stt/runtime.py` so the runner can delegate STT-specific feature extraction and decode behavior without growing more STT logic. No behavior change intended. Signed-off-by: Yuan Lik Xun <lxyuan0420@gmail.com>
Signed-off-by: Yuan Lik Xun <lxyuan0420@gmail.com>
Signed-off-by: Yuan Lik Xun <lxyuan0420@gmail.com>
Signed-off-by: Yuan Lik Xun <lxyuan0420@gmail.com>
Signed-off-by: Yuan Lik Xun <lxyuan0420@gmail.com>
LxYuan0420
force-pushed
the
refactor/stt-runtime-executor
branch
from
be33758 to
b3f5843
Compare
Signed-off-by: Yuan Lik Xun <lxyuan0420@gmail.com>
Signed-off-by: Yuan Lik Xun <lxyuan0420@gmail.com>
ericcurtin
approved these changes
Mar 19, 2026
WindChimeRan
added a commit
to WindChimeRan/vllm-metal
that referenced
this pull request
Mar 20, 2026
Resolve conflict in model_runner.py: keep STTExecutor class (from vllm-project#173), drop stale MAX_PACKED_PREFILL_TOKENS constant (removed in this branch). Signed-off-by: ran <hzz5361@psu.edu>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR is:
model_runnerinto a dedicated runtime module.stt.transcribemodule and keep the public STT API honest.Next:
hf_configand serve compatibility glue into a clearer compat-focused module.