Conversation
Introduce a device abstraction layer (cosyvoice/utils/device.py) that unifies CUDA, MPS, and CPU device management. Replace all hardcoded CUDA-specific code paths in the inference pipeline with device-agnostic alternatives, enabling CosyVoice to run natively on Apple Silicon Macs. Key changes: - Device abstraction: get_device(), get_stream_context(), get_autocast_context(), empty_cache() - model.py: Replace CUDA device init, streams, AMP, and cache clearing across CosyVoiceModel, CosyVoice2Model, CosyVoice3Model - cosyvoice.py: MPS-aware feature gates (TRT/vLLM require CUDA, JIT/fp16 require any GPU) - frontend.py: CoreMLExecutionProvider support for ONNX Runtime - common.py: Guard torch.cuda.manual_seed_all for non-CUDA environments - requirements.txt: Remove CUDA-only index URLs, loosen PyTorch version - setup_macos.sh: One-command setup script for Apple Silicon Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
jasagiri
force-pushed
the
feat/apple-silicon
branch
from
5d2a2c9 to
029f931
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Device abstraction layer for CUDA/MPS/CPU, enabling native Apple Silicon inference.
See upstream PR: FunAudioLLM#1869
🤖 Generated with Claude Code