mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2026-04-25 01:03:35 +00:00
8daee26989
* add infer_struct and infer_config * update codes * change InferConfig * Add hf_model_config to the engine * rm _get_hf_model_config * update codes * made adjustments according to the feedback from the reviewer. * update codes * add ci test for config and struct * Add the logic of the inference engine * update engine and test * Recover cache_manager.py * add logger * fix conflict * update codes * update codes * update model and tokenizer * fix add the logic about shardformer * change kvcache_manager docstring * add policy * fix ci bug in test_kvcache_manager.py * remove codes related o tokenizer and move model_policy * fix code style * add ordered_set to requirements-infer.txt * Delete extra empty lines * add ordered_set to requirements-test.txt
25 lines
588 B
Plaintext
25 lines
588 B
Plaintext
diffusers
|
|
fbgemm-gpu==0.2.0
|
|
ordered_set
|
|
pytest
|
|
coverage==7.2.3
|
|
git+https://github.com/hpcaitech/pytest-testmon
|
|
torchvision
|
|
transformers==4.33.0
|
|
timm
|
|
titans
|
|
torchaudio
|
|
torchx-nightly==2022.6.29 # torchrec 0.2.0 requires torchx-nightly. This package is updated every day. We fix the version to a specific date to avoid breaking changes.
|
|
torchrec==0.2.0
|
|
contexttimer
|
|
einops
|
|
triton==2.1.0
|
|
requests==2.27.1 # downgrade to avoid huggingface error https://github.com/huggingface/transformers/issues/17611
|
|
SentencePiece
|
|
ninja
|
|
flash_attn
|
|
datasets
|
|
pydantic
|
|
ray
|
|
#auto-gptq now not support torch1.12
|