AlpinDale bf88c8567e feat: mamba model support (#674) 6 months ago
..
backends bf88c8567e feat: mamba model support (#674) 6 months ago
ops e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668) 6 months ago
__init__.py a0e446a17d feat: initial encoder-decoder support with BART model (#633) 6 months ago
layer.py bf88c8567e feat: mamba model support (#674) 6 months ago
selector.py bf88c8567e feat: mamba model support (#674) 6 months ago