boiwhat/Ace-Step-v1.5

fix max audio code id

reverse fix

fix max audio code id

update tech report link

add acemusic link

fix cfg kv block allocate

enforce upload audio duration limits

fix duration

set default_concurrency_limit & set bs=2 no interactive

bigger sample btn

fix ffmpeg issue

fix ffmpeg full install

load audio fallback

fix torchcodec ffmpeg

fix transformers version

fix CUDA Graph mismatch in nanovllm

fix cover load src audio using ffmpeg

hide files list

support shift3 download

update project page url

refact ui (fix repaint/cover score bug)

refact ui

fix audio play position reset

fix build-essential

fix Qwen3ForCausalLM has no attribute

fix Qwen3ForCausalLM has no attribute

fix transformer version issue

fix data permission

support nano vllm docker

support nano vllm docker

support nano vllm

fix: model id

fix service mode

fix: auto download model

feat: gradio version

feat: update gradio version

feat: change flash-atten

fix: requirements

fix: update model repo_id

feat: update readme

fix: change python version

feat: update git lfs

feat: add packages

feat: huggingface space app

Merge branch 'main' into huggingface_space

feat: huggingface_space support

Merge pull request #17 from ace-step/add_model_zoo

add model zoo

add model zoo

Merge pull request #16 from ace-step/add_readme