Sihan Chen

Add Whisper static generation

10

# What does this PR do? Add static KV cache for Whisper family models. Previously it takes huge amount of time to do the Whisper inference (each first inference for...

Fail to do Qwen2-VL-72B inference with StaticCache

4

### System Info ```shell +-----------------------------------------------------------------------------+ | HL-SMI Version: hl-1.19.2-fw-57.2.4.0 | | Driver Version: 1.19.2-ff37fea | |-------------------------------+----------------------+----------------------+ ``` ### Information - [x] The official example scripts - [ ] My own...

Langchain Chroma bug when add documents

1

### Describe the bug Hi, I'm using the latest huggingface_hub `0.28.1` and it will crash and show messy embedding output when doing `vectordb.add_documents`. Fallback to `0.27.1` can fix the issue....