AlpinDale 22422d962b feat: add cuda sampling kernels for top_k and top_p | 2 månader sedan | |
---|---|---|
.. | ||
latency.py | f1d0b77c92 [0.6.0] Release Candidate (#481) | 5 månader sedan |
serving.py | f1d0b77c92 [0.6.0] Release Candidate (#481) | 5 månader sedan |
throughput.py | 22422d962b feat: add cuda sampling kernels for top_k and top_p | 2 månader sedan |