v0.3.8
[Fix/Inference] Add unsupported auto-policy error message (#5730)
[Inference] Fix Inference Generation Config and Sampling (#5710)
[Feat]Inference RPC Server Support (#5705)
[Fix] Llama3 Load/Omit CheckpointIO Temporarily (#5717)
[Inference]Fix readme and example for API server (#5742)
[example] Update Inference Example (#5725)
[doc] updated inference readme (#5343)
[Inference]Adapt repetition_penalty and no_repeat_ngram_size (#5708)
add paged-attetionv2: support seq length split across thread block (#5707)
[fix] pytest and fix dyn grid bug
[Online Server] Chat Api for streaming and not streaming response (#5470)