v0.1.7

dongjiyingdjy released this 19 Mar 02:53

· 1202 commits to main since this release

features

support int4 (experimental) on Qwen GPTQ
support V100 fmha
support Bert
Optimize VIT Engine by TensorRT

refactor

refactor schedule strategy, malloc kv cache in schedule new stream
refactor MOE

docs

update supported models

Assets 4