Issues: vectorch-ai/ScaleLLM
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Introducing a ring attention mechanism for handling long contexts
#164
opened Apr 28, 2024 by
guocuimi
Adding more Prometheus metrics and creating a Grafana dashboard for monitoring.
#158
opened Apr 28, 2024 by
guocuimi
Adding more bechmarks and unittests for kernels and dependencies
#157
opened Apr 28, 2024 by
guocuimi
GPU Arch: Turing architecture (sm75)
enhancement
New feature or request
#152
opened Apr 28, 2024 by
guocuimi
Adding support for Apple chips
enhancement
New feature or request
#151
opened Apr 28, 2024 by
guocuimi
Introducing multi-modal models (LLaVA model)
enhancement
New feature or request
#150
opened Apr 28, 2024 by
guocuimi
Implementing MoE (Mixture of Experts) kernels
performance
Improvements to performance
#149
opened Apr 28, 2024 by
guocuimi
Implementing fused FFN (Feed-Forward Network) to enhance efficiency
performance
Improvements to performance
#148
opened Apr 28, 2024 by
guocuimi
Exploring the feasibility of adopting the flashinfer library
performance
Improvements to performance
#147
opened Apr 28, 2024 by
guocuimi
Exploring lookahead decoding support
enhancement
New feature or request
#146
opened Apr 28, 2024 by
guocuimi
cuda graph capture may occasionally become stuck with multiple gpus.
bug
Something isn't working
enhancement
New feature or request
#131
opened Apr 18, 2024 by
guocuimi
does the current openai-copatible-API support function calls?
enhancement
New feature or request
#121
opened Apr 10, 2024 by
lyj555
is there any way or chance to use flash_attn 1.x ? to support more gpus
#69
opened Mar 7, 2024 by
dalamudx
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.