Antoni Baum 21d93c140d Optimize Mixtral with expert parallelism (#2090)

2023-12-13 23:55:07 -08:00

..

__init__.py

Optimize Mixtral with expert parallelism (#2090)

2023-12-13 23:55:07 -08:00

aquila.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

baichuan.py

[Minor] Fix code style for baichuan (#2003)

2023-12-09 19:24:29 -08:00

bloom.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

chatglm.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

falcon.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

gpt2.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

gpt_bigcode.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

gpt_j.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

gpt_neox.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

internlm.py

Make InternLM follow rope_scaling in config.json (#1956)

2023-12-07 08:32:08 -08:00

llama.py

[Minor] Add comment on skipping rope caches (#2004)

2023-12-10 10:04:12 -08:00

mistral.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

mixtral.py

Optimize Mixtral with expert parallelism (#2090)

2023-12-13 23:55:07 -08:00

mpt.py

Support MPT with GQA (#1938)

2023-12-12 10:16:05 -08:00

opt.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

phi_1_5.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

qwen.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

yi.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00