Skip to content

Add vLLM cache to TTS model #4

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

Merged
PatrickCmd merged 2 commits into from
Feb 3, 2026
Merged

Add vLLM cache to TTS model #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
43aa1df
update
huwenjie333 Jan 9, 2026
8ae1ac7
comments
huwenjie333 Jan 9, 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
3 changes: 2 additions & 1 deletion modal-deploy/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,8 +34,9 @@ modal setup

6. test the deployed model with the client script, for example:
```
cd Sunflower32b-Ultravox
python client.py \
--app-name Sunflower32b-Ultravox \
--prompt "Translate to English: " \
--audio_file "../sunflower-ultravox-vllm/audios/context_eng_1.wav"
--audio_file "../../sunflower-ultravox-vllm/audios/context_eng_1.wav"
```
6 changes: 5 additions & 1 deletion modal-deploy/spark-tts-salt/vllm_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,8 +60,11 @@

# cache model weights with Modal Volumes
hf_cache_vol = modal.Volume.from_name("huggingface-cache", create_if_missing=True)
HF_CACHE_DIR = "/root/.cache/huggingface"
# cache some of vLLM's compilation artifacts in a Modal Volume.
vllm_cache_vol = modal.Volume.from_name("vllm-cache", create_if_missing=True)

HF_CACHE_DIR = "/root/.cache/huggingface"
VLLM_CACHE_DIR = "/root/.cache/vllm"

# ## The TTS model class

Expand All @@ -78,6 +81,7 @@
secrets=[modal.Secret.from_name("huggingface-read")],
volumes={
HF_CACHE_DIR: hf_cache_vol,
VLLM_CACHE_DIR: vllm_cache_vol,
}
)
@modal.concurrent(max_inputs=10)
Expand Down
Loading