huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update docs/source/conceptual/tensor_parallelism.md

Browse Source 
Co-authored-by: Omar Sanseviero <osanseviero@gmail.com>
This commit is contained in:
Merve Noyan 2023-08-23 15:45:12 +03:00 committed by GitHub
parent 27baaeffe0
commit 1e828f33c0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/conceptual/tensor_parallelism.md
View File

@ -1,6 +1,6 @@
# Tensor Parallelism # Tensor Parallelism
Tensor parallelism (also called horizontal model parallelism) is a technique used to fit a large model in multiple GPUs. Intermediate outputs between ranks are sent and received from one rank to another in a synchronous or asynchronous manner. When multiplying input with weights for inference, multiplying input with weights directly is equivalent to dividing the weight matrix column-wise, multiplying each column with input separately, and then concatenating the separate outputs like below 👇 Tensor parallelism is a technique used to fit a large model in multiple GPUs. Intermediate outputs between GPUs are sent and received from one GPU to another in a synchronous or asynchronous manner. For example, when multiplying the input tensors with the first weights tensor, multiplying both tensors is equivalent to splitting the weight tensor column-wise, multiplying each column with input separately, and then concatenating the separate outputs like below 👇
![Image courtesy of Anton Lozkhov](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/TP.png) ![Image courtesy of Anton Lozkhov](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/TP.png)