Skip to content

fix(moe): fit Qwen3.8 Flash Next FP8 banks across host and GPU memory - #602

Open
yunwei37 wants to merge 3 commits into
FlashML-org:mainfrom
yunwei37:codex/fp8-host-gpu-banks
Open

yunwei37 wants to merge 3 commits into
FlashML-org:mainfrom
yunwei37:codex/fp8-host-gpu-banks

Enhance your code review process with GitHub Actions

GitHub Actions make it easy to automate all your software workflows, now with world-class CI/CD.
Build, test, and deploy your code right from GitHub. Learn more about GitHub Actions.

Linux, macOS, Windows, and containers
Linux, macOS, Windows, and containers
Matrix builds
Matrix builds
Any language
Any language
Live logs
Live logs
Built-in secret store
Built-in secret store
Multi-container testing
Multi-container testing