Cody YuandGitHub a3a73ab069 [Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893) ...

The 2nd PR for #4532.

This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).

2024-05-22 13:28:20 -07:00

..

benchmark_aqlm.py

[Core]refactor aqlm quant ops (#4351)

2024-04-25 15:03:56 -04:00

benchmark_marlin.py

Add marlin unit tests and marlin benchmark script (#4815)

2024-05-16 09:36:49 -04:00

benchmark_mixtral_moe.py

[Kernel] Update fused_moe tuning script for FP8 (#4457)

2024-05-01 11:47:38 -07:00

benchmark_paged_attention.py

[Misc] Load FP8 kv-cache scaling factors from checkpoints (#4893)

2024-05-22 13:28:20 -07:00

benchmark_rope.py

[CI] Try introducing isort. (#3495)

2024-03-25 07:59:47 -07:00

benchmark_shapes.py

Add marlin unit tests and marlin benchmark script (#4815)

2024-05-16 09:36:49 -04:00