Philipp MoritzandWoosuk Kwon 12628d3c78 [Kernel] Optimize FP8 support for MoE kernel / Mixtral via static scales (#4343) ...

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2024-04-27 04:49:59 +00:00

..

guided_decoding

[Bugfix] Add fix for JSON whitespace (#4189)

2024-04-19 20:49:22 -07:00

layers

[Kernel] Optimize FP8 support for MoE kernel / Mixtral via static scales (#4343)

2024-04-27 04:49:59 +00:00

model_loader

[Misc][Refactor] Generalize linear_method to be quant_method (#4373)

2024-04-26 16:41:14 -04:00

models

[Kernel] Optimize FP8 support for MoE kernel / Mixtral via static scales (#4343)

2024-04-27 04:49:59 +00:00

__init__.py

[Core] Refactor Attention Take 2 (#3462)

2024-03-25 04:39:33 +00:00

sampling_metadata.py

[Core] Refactoring sampler and support prompt logprob for chunked prefill (#4309)

2024-04-26 13:02:02 +00:00

utils.py

[Hardware][Neuron] Refactor neuron support (#3471)

2024-03-22 01:22:17 +00:00