mstar-project/mstar

`torch._dynamo.config` settings in `mstar/engine/__init__.py` are silently ignored on the GPU thread (torch 2.13) 22 days ago

bug good first issue

mstar-project/mstar

52

A high-performance, universal serving framework for any-to-any models.

Python

#agentic-infrastructure#diffusion#distributed-systems#high-performance-computing#inference#multimodal#robotics#serving-infrastructure#speech-language-model#unified-multimodal-models#vision-language-action-model#vision-language-models#world-models

Minor: Warnings related to TP 22 days ago

bug good first issue low priority

mstar-project/mstar

52

A high-performance, universal serving framework for any-to-any models.

Python

#agentic-infrastructure#diffusion#distributed-systems#high-performance-computing#inference#multimodal#robotics#serving-infrastructure#speech-language-model#unified-multimodal-models#vision-language-action-model#vision-language-models#world-models

Clean up and consolidate the testing stack about 2 months ago

good first issue

mstar-project/mstar

52

A high-performance, universal serving framework for any-to-any models.

Python

#agentic-infrastructure#diffusion#distributed-systems#high-performance-computing#inference#multimodal#robotics#serving-infrastructure#speech-language-model#unified-multimodal-models#vision-language-action-model#vision-language-models#world-models

Port the Qwen3-Omni multimodal encoders into M* and optimize them about 2 months ago

enhancement good first issue

mstar-project/mstar

52

A high-performance, universal serving framework for any-to-any models.

Python

#agentic-infrastructure#diffusion#distributed-systems#high-performance-computing#inference#multimodal#robotics#serving-infrastructure#speech-language-model#unified-multimodal-models#vision-language-action-model#vision-language-models#world-models

Open Issues Need Help