Skip to content

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.

Sign up for GitHub

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

33 Open 43 Closed
33 Open 43 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

ScaleAttention: a custom CUDA kernel, optimized for inference. performance Improvements to performance roadmap
#356 opened Jan 1, 2025 by guocuimi
RuntimeError: Timed out
#310 opened Aug 16, 2024 by spongxin
1
Is there any plans to support Int8 weight quant ?
#276 opened Jul 18, 2024 by sitabulaixizawaluduo
2
[Issue] Qwen-14B-Chat init fail and performance issue.
#275 opened Jul 16, 2024 by liutongxuan
2
LoRA: QLoRA/S-LoRA: Serving thousands of LoRA adapters
#166 opened Apr 28, 2024 by guocuimi
Introducing the Mamba model
#165 opened Apr 28, 2024 by guocuimi
Introducing a ring attention mechanism for handling long contexts
#164 opened Apr 28, 2024 by guocuimi
Quantization: Supporting FP8 for both models and KV caches
#163 opened Apr 28, 2024 by guocuimi
Enhancing documentation for improved usability
#162 opened Apr 28, 2024 by guocuimi
@guocuimi
Exploring other chips such as TPU, etc. backlog
#160 opened Apr 28, 2024 by guocuimi
Loosening coupling with PyTorch for easy deployment
#159 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
Extending support to macOS and Windows platforms backlog
#156 opened Apr 28, 2024 by guocuimi
Structural Decoding: Function Calling backlog
#155 opened Apr 28, 2024 by guocuimi
Structural Decoding: Json format
#154 opened Apr 28, 2024 by guocuimi
Structural Decoding: Json format
#153 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
@liutongxuan @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
ScaleLLM vs vLLM in performance roadmap
#144 opened Apr 27, 2024 by WangErXiao
20
ProTip! Add no:assignee to see everything that’s not assigned.