Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update llame inference README file #57

Closed
wants to merge 1 commit into from
Closed

Update llame inference README file #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions MLPERF4.0/Inference/llama/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,12 +34,14 @@ echo "vm.nr_hugepages=100000" | sudo tee -a /etc/sysctl.conf
Clone this repository and switch to the branch that matches your Intel Gaudi software version.
You can run the [`hl-smi`](https://docs.habana.ai/en/latest/System_Management_Tools_Guide/System_Management_Tools.html#hl-smi-utility-options) utility to determine the Intel Gaudi software version.
```bash
mkdir -p /path/to/Intel-HabanaLabs
cd /path/to/Intel-HabanaLabs
git clone --recurse-submodules -b [Intel Gaudi software version] https://github.com/HabanaAI/Model-References
```

### Prepare `Intel-HabanaLabs` MLPerf Inference Container
```bash
export INTEL_HABANALABS_DIR=$PWD/Model-References/MLPERF4.0/Inference
export INTEL_HABANALABS_DIR=/path/to/Intel-HabanaLabs
```

```bash
Expand Down Expand Up @@ -111,7 +113,7 @@ The same script was submitted for both 99 and 99.9 benchmarks - no additional im
Source the necessary files:

```bash
cd /root/Intel-HabanaLabs
cd /root/Intel-HabanaLabs/Model-References/MLPERF4.0/Inference/
source functions.sh
```

Expand Down
1 change: 1 addition & 0 deletions MLPERF4.0/Inference/llama/setup_tgi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ unzip -o $PROTOC_ZIP -d /usr/local 'include/*'
rm -f $PROTOC_ZIP
# prepare TGI with Gaudi support
cd "$script_dir/tgi-gaudi/"
git config --global --add safe.directory "$script_dir/tgi-gaudi"
git checkout habana-main
pushd $HOME
mkdir repos
Expand Down