DeepSpeed
10a1df25
- Merge branch 'add-llama2-support' of github.com:microsoft/DeepSpeed into add-llama2-support
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Hide Minimap (CTRL+M)
Commit
1 year ago
Merge branch 'add-llama2-support' of github.com:microsoft/DeepSpeed into add-llama2-support
References
#4351 - DS-Inference Quantization refresh: Fix several issues and add more features
#4313 - Add the policy to run llama model from the official repo
Author
Reza Yazdani
Parents
a87860d2
297a15cd
Files
8
csrc/transformer/inference/csrc
pt_binding.cpp
deepspeed
module_inject
containers
__init__.py
internlm.py
replace_policy.py
utils.py
ops/transformer/inference
ds_attention.py
op_binding
mlp_gemm.py
qkv_gemm.py
Loading