rename PERSISTENT_VOLUME to MODEL_VOLUME in legacy documentation

tenstorrent · Jan 14, 2025 · 23b8495 · 23b8495
1 parent 1a15966
commit 23b8495
Show file tree

Hide file tree

Showing 5 changed files with 14 additions and 14 deletions.
diff --git a/tt-metal-llama3-70b/README.md b/tt-metal-llama3-70b/README.md
@@ -27,15 +27,15 @@ Container will run `gunicorn --config gunicorn.conf.py` and start the inference
 ```bash
 cd tt-inference-server
 # make sure if you already set up the model weights and cache you use the correct persistent volume
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama-3.1-70b-instructv0.0.1/
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama-3.1-70b-instructv0.0.1/
 docker run \
   --rm \
   -it \
   --env-file tt-metal-llama3-70b/.env \
   --cap-add ALL \
   --device /dev/tenstorrent:/dev/tenstorrent \
   --volume /dev/hugepages-1G:/dev/hugepages-1G:rw \
-  --volume ${PERSISTENT_VOLUME?ERROR env var PERSISTENT_VOLUME must be set}:/home/user/cache_root:rw \
+  --volume ${MODEL_VOLUME?ERROR env var MODEL_VOLUME must be set}:/home/user/cache_root:rw \
   --shm-size 32G \
   --publish 7000:7000 \
   ghcr.io/tenstorrent/tt-inference-server/tt-metal-llama3-70b-src-base-inference:v0.0.1-tt-metal-v0.52.0-rc31-9d3be887987b
@@ -81,15 +81,15 @@ Run container overriding the entrypoint `CMD` with an interactive bash shell:
 ```bash
 cd tt-inference-server
 # Ensure that if you have already set up the model weights and cache, you are using the correct persistent volume.
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3.1-70bv0.0.1
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3.1-70bv0.0.1
 docker run \
   --rm \
   -it \
   --env-file tt-metal-llama3-70b/.env \
   --cap-add ALL \
   --device /dev/tenstorrent:/dev/tenstorrent \
   --volume /dev/hugepages-1G:/dev/hugepages-1G:rw \
-  --volume ${PERSISTENT_VOLUME?ERROR env var PERSISTENT_VOLUME must be set}:/home/user/cache_root:rw \
+  --volume ${MODEL_VOLUME?ERROR env var MODEL_VOLUME must be set}:/home/user/cache_root:rw \
   --shm-size 32G \
   --publish 7000:7000 \
   ghcr.io/tenstorrent/tt-inference-server/tt-metal-llama3-70b-src-base-inference:v0.0.1-tt-metal-v0.52.0-rc31-9d3be887987b bash

diff --git a/tt-metal-llama3-70b/docs/development.md b/tt-metal-llama3-70b/docs/development.md
@@ -5,15 +5,15 @@ Add the src code as a volume mount so that it can be editted and rerun inside th
 ```bash
 cd cd tt-inference-server
 # make sure if you already set up the model weights and cache you use the correct persistent volume
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3.1-70bv0.0.1
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3.1-70bv0.0.1
 docker run \
   -it \
   --rm \
   --env-file tt-metal-llama3-70b/.env \
   --cap-add ALL \
   --device /dev/tenstorrent:/dev/tenstorrent \
   --volume /dev/hugepages-1G:/dev/hugepages-1G:rw \
-  --volume ${PERSISTENT_VOLUME?ERROR env var PERSISTENT_VOLUME must be set}:/home/user/cache_root:rw \
+  --volume ${MODEL_VOLUME?ERROR env var MODEL_VOLUME must be set}:/home/user/cache_root:rw \
   --volume $PWD/tt-metal-llama3-70b/src:/home/user/tt-metal-llama3-70b/src:rw \
   --shm-size 32G \
   --publish 7000:7000 \

diff --git a/tt-metal-llama3-70b/docs/faq.md b/tt-metal-llama3-70b/docs/faq.md
@@ -89,7 +89,7 @@ download weights:
 ```bash
 cd tt-inference-server
 # make sure if you already set up the model weights and cache you use the correct persistent volume
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3-70bv0.0.1
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3-70bv0.0.1
 # create directories in persistent volume
 mkdir -p ${PERSISTENT_VOLUME}/model_weights/repacked-llama-3-70b-instruct
 mkdir -p ${PERSISTENT_VOLUME}/tt_metal_cache/cache_repacked-llama-3-70b-instruct
@@ -115,7 +115,7 @@ python models/demos/t3000/llama2_70b/scripts/repack_weights.py /home/user/cache_
 
 ```bash
 # need to set path environment variables for demo scripts using different weights
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3-70bv0.0.1
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3-70bv0.0.1
 export LLAMA_VERSION=llama3
 export LLAMA3_CKPT_DIR=/home/user/cache_root/model_weights/repacked-llama-3-70b-instruct
 export LLAMA3_TOKENIZER_PATH=/home/user/cache_root/model_weights/repacked-llama-3-70b-instruct/tokenizer.model
@@ -128,7 +128,7 @@ download weights:
 ```bash
 cd tt-inference-server
 # make sure if you already set up the model weights and cache you use the correct persistent volume
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama2-70bv0.0.1
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama2-70bv0.0.1
 # create directories in persistent volume
 mkdir -p ${PERSISTENT_VOLUME}/model_weights/repacked-llama-2-70b-chat
 mkdir -p ${PERSISTENT_VOLUME}/tt_metal_cache/cache_repacked-llama-2-70b-chat
@@ -155,7 +155,7 @@ python models/demos/t3000/llama2_70b/scripts/repack_weights.py /home/user/cache_
 
 ```bash
 # need to set path environment variables for demo scripts using different weights
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama2-70bv0.0.1
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama2-70bv0.0.1
 export LLAMA_VERSION=llama2
 export LLAMA3_CKPT_DIR=/home/user/cache_root/model_weights/repacked-llama-2-70b-instruct
 export LLAMA3_TOKENIZER_PATH=/home/user/cache_root/model_weights/repacked-llama-2-70b-instruct/tokenizer.model

diff --git a/tt-metal-llama3-70b/docs/manual_setup_guide.md b/tt-metal-llama3-70b/docs/manual_setup_guide.md
@@ -91,7 +91,7 @@ mkdir -p ${PERSISTENT_VOLUME_ROOT}
 ```bash
 cd tt-inference-server
 # make sure if you already set up the model weights and cache you use the correct persistent volume
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3.1-70bv0.0.1
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-llama3.1-70bv0.0.1
 # create directories in persistent volume
 mkdir -p ${PERSISTENT_VOLUME}/model_weights/repacked-llama-3.1-70b-instruct
 mkdir -p ${PERSISTENT_VOLUME}/tt_metal_cache/cache_repacked-llama-3.1-70b-instruct
@@ -118,7 +118,7 @@ docker run \
   --cap-add ALL \
   --device /dev/tenstorrent:/dev/tenstorrent \
   --volume /dev/hugepages-1G:/dev/hugepages-1G:rw \
-  --volume ${PERSISTENT_VOLUME?ERROR env var PERSISTENT_VOLUME must be set}:/home/user/cache_root:rw \
+  --volume ${MODEL_VOLUME?ERROR env var MODEL_VOLUME must be set}:/home/user/cache_root:rw \
   --shm-size 32G \
   --publish 7000:7000 \
   ghcr.io/tenstorrent/tt-inference-server/tt-metal-llama3-70b-src-base-inference:v0.0.1-tt-metal-v0.52.0-rc31-9d3be887987b bash

diff --git a/tt-metal-mistral-7b/README.md b/tt-metal-mistral-7b/README.md
@@ -20,7 +20,7 @@ If you're starting from scratch or the quick run is not working see the [setup](
 export JWT_SECRET=<your-secure-secret>
 cd tt-inference-server
 # make sure if you already set up the model weights and cache you use the correct persistent volume
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-mistral-7bv0.0.2
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-mistral-7bv0.0.2
 docker run \
   --rm \
   -it \
@@ -86,7 +86,7 @@ sudo chmod -R g+w persistent_volume/volume_id_tt-metal-mistral-7bv0.0.2
 cd tt-inference-server
 # make sure if you already set up the model weights and cache you use the correct persistent volume
 export JWT_SECRET=<your-secure-secret>
-export PERSISTENT_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-mistral-7bv0.0.2
+export MODEL_VOLUME=$PWD/persistent_volume/volume_id_tt-metal-mistral-7bv0.0.2
 docker run \
   --rm \
   -it \