Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
DeepSpeed-FastGen: High-Throughput for LLMs via MII and DeepSpeed-Inference
github.com/microsoft
2 points
CharlesW
3 years ago
No comment yet
DeepSpeed-FastGen: High-Throughput for LLMs via MII and DeepSpeed-Inference | Heykuki News