Yueyang Pan

There are two suggestions for this project. 1. Currently, this project mainly contains introductory courses at the bachelor level. I am thinking whether it would be beneficial to include good...

Cargo test failed for two cases on bare metal

1

**Describe the bug** A clear and concise description of what the bug is. I cloned hermit on the server and ran the `cargo test`. There are two failed tests. ```rust...

[Bug]: Random model output using sglang backend server

2

# The description of the bug: I am using AWS P3 instances with 4 V100 GPUs, and the system configuration is in the section below. I ran the example from...

[Core] Enable Memory Tiering for vLLM

5

This is the following PR of #7697. This PR introduces 3 major functionalities: 1. Context Caching with TTL support is also a huge drive for memory demand. 2. Blockwise swapping...

## Motivation Add clamp to llavavid model so that the placeholder for video input won't casue out-of-bound error when running LLaVA-NeXT-Video-7B using `srt_example_llava_v.py`. The error is shown below.  ##...