Jeff Rasley da84e60d98 add missing license info to top of all source code (#2889) | 1 year ago | |
---|---|---|
.. | ||
__init__.py | da84e60d98 add missing license info to top of all source code (#2889) | 1 year ago |
experts.py | e46d808a1b MoE inference + PR-MoE model support (#1705) | 2 years ago |
layer.py | 18713c6838 Updating API docs (#2586) | 1 year ago |
mappings.py | 5fe9d61065 Tensor parallelism for Mixture of Experts (#2074) | 2 years ago |
sharded_moe.py | 80f94c10c5 fix #2240: wrong time unit in flops_profiler (#2241) | 2 years ago |
utils.py | da84e60d98 add missing license info to top of all source code (#2889) | 1 year ago |