From 43aa1dfaa935114eb4092be0e1fb7ba56372d913 Mon Sep 17 00:00:00 2001 From: huwenjie333 Date: Fri, 9 Jan 2026 14:18:20 +0300 Subject: [PATCH 1/2] update --- modal-deploy/README.md | 3 ++- modal-deploy/spark-tts-salt/vllm_inference.py | 5 ++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/modal-deploy/README.md b/modal-deploy/README.md index 1213d7dd..767e613b 100644 --- a/modal-deploy/README.md +++ b/modal-deploy/README.md @@ -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" ``` \ No newline at end of file diff --git a/modal-deploy/spark-tts-salt/vllm_inference.py b/modal-deploy/spark-tts-salt/vllm_inference.py index 17b28d17..5b055ed8 100644 --- a/modal-deploy/spark-tts-salt/vllm_inference.py +++ b/modal-deploy/spark-tts-salt/vllm_inference.py @@ -60,8 +60,10 @@ # 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" +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 @@ -78,6 +80,7 @@ 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) From 8ae1ac7bf3e704c011f9c93e719258564f70ccf8 Mon Sep 17 00:00:00 2001 From: huwenjie333 Date: Fri, 9 Jan 2026 14:52:51 +0300 Subject: [PATCH 2/2] comments --- modal-deploy/spark-tts-salt/vllm_inference.py | 1 + 1 file changed, 1 insertion(+) diff --git a/modal-deploy/spark-tts-salt/vllm_inference.py b/modal-deploy/spark-tts-salt/vllm_inference.py index 5b055ed8..c6fe806a 100644 --- a/modal-deploy/spark-tts-salt/vllm_inference.py +++ b/modal-deploy/spark-tts-salt/vllm_inference.py @@ -60,6 +60,7 @@ # cache model weights with Modal Volumes hf_cache_vol = modal.Volume.from_name("huggingface-cache", create_if_missing=True) +# 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"