Roy eed74a558f Simplify weight loading logic (#2133)

2023-12-16 12:41:23 -08:00

..

__init__.py

Optimize Mixtral with expert parallelism (#2090)

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

aquila.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

baichuan.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

bloom.py

Refactor Worker & InputMetadata (#1843)

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

chatglm.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

falcon.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

gpt2.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

gpt_bigcode.py

Refactor Worker & InputMetadata (#1843)

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

gpt_j.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

gpt_neox.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

internlm.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

llama.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

mistral.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

mixtral.py

Simplify weight loading logic (#2133)

2023-12-16 12:41:23 -08:00

mpt.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

opt.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

phi_1_5.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

qwen.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

yi.py

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00