Skip to content

Commit

Permalink
Browse files Browse the repository at this point in the history
 into llama32-TG
  • Loading branch information
sraizada-tt committed Dec 6, 2024
2 parents 1511022 + 4e4e439 commit 9b53818
Show file tree
Hide file tree
Showing 184 changed files with 9,157 additions and 2,809 deletions.
4 changes: 2 additions & 2 deletions .github/actions/docker-run/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ inputs:
docker_os_arch:
description: 'Docker image architecture'
required: false
default: ubuntu-20.04-amd64
default: tt-metalium/ubuntu-20.04-amd64
docker_username:
description: docker login username
required: true
Expand Down Expand Up @@ -89,7 +89,7 @@ runs:
set -eu
install_wheel=${{ inputs.install_wheel }}
if [[ "${install_wheel,,}" == "true" ]]; then
if [ "${install_wheel,,}" == "true" ]; then
WHEEL_FILENAME=$(ls -1 *.whl)
pip3 install "$WHEEL_FILENAME"
fi
Expand Down
4 changes: 2 additions & 2 deletions .github/actions/generate-docker-tag/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,8 @@ runs:
- name: Determine Full Docker Image Tag
shell: bash
run: |
echo "TT_METAL_DOCKER_IMAGE_TAG=ghcr.io/${{ github.repository }}/tt-metalium/${{ inputs.image }}:${{ env.IMAGE_TAG }}" >> $GITHUB_ENV
echo "TT_METAL_REF_IMAGE_TAG=ghcr.io/${{ github.repository }}/tt-metalium/${{ inputs.image }}:latest" >> $GITHUB_ENV
echo "TT_METAL_DOCKER_IMAGE_TAG=ghcr.io/${{ github.repository }}/${{ inputs.image }}:${{ env.IMAGE_TAG }}" >> $GITHUB_ENV
echo "TT_METAL_REF_IMAGE_TAG=ghcr.io/${{ github.repository }}/${{ inputs.image }}:latest" >> $GITHUB_ENV
- name: Output Docker Image Tag
shell: bash
run: |
Expand Down
1 change: 0 additions & 1 deletion .github/workflows/all-post-commit-workflows.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -159,7 +159,6 @@ jobs:
secrets: inherit
with:
os: ubuntu-22.04-amd64
if: github.event_name == 'push'
tt-train-cpp-unit-tests:
needs: build-artifact
secrets: inherit
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/build-artifact.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ jobs:
id: generate-docker-tag
uses: ./.github/actions/generate-docker-tag
with:
image: ${{ inputs.os }}
image: tt-metalium/${{ inputs.os }}
- name: Docker login
uses: docker/login-action@v3
with:
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/build-docker-artifact.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ jobs:
- name: Determine docker image tag
uses: ./.github/actions/generate-docker-tag
with:
image: ${{ inputs.os }}
image: tt-metalium/${{ inputs.os }}
- name: Build Docker image and push to GHCR
if: steps.changed-files-specific.outputs.any_changed == 'true'
uses: docker/build-push-action@v6
Expand Down
3 changes: 1 addition & 2 deletions .github/workflows/build.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -50,14 +50,13 @@ jobs:
with:
docker_username: ${{ github.actor }}
docker_password: ${{ secrets.GITHUB_TOKEN }}
docker_image_arch: ${{ inputs.arch }}
docker_opts: |
-e ARCH_NAME=${{ matrix.arch }}
--group-add 1457
-v /home/ubuntu/.ccache-ci:/home/ubuntu/.ccache
-e CCACHE_DIR=/home/ubuntu/.ccache
-v /mnt/MLPerf/ccache:/mnt/MLPerf/ccache
docker_os_arch: ${{ matrix.build.os }}-amd64
docker_os_arch: tt-metalium/${{ matrix.build.os }}-amd64
run_args: |
set -eu # basic shell hygiene
set -x
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/code-analysis.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ jobs:
id: generate-docker-tag
uses: ./.github/actions/generate-docker-tag
with:
image: ${{ inputs.os }}
image: tt-metalium/${{ inputs.os }}
- name: Docker login
uses: docker/login-action@v3
with:
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/cpp-ttnn-project.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ jobs:
id: generate-docker-tag
uses: ./.github/actions/generate-docker-tag
with:
image: ubuntu-22.04-amd64
image: tt-metalium/ubuntu-22.04-amd64
- name: Docker login
uses: docker/login-action@v3
with:
Expand Down
2 changes: 2 additions & 0 deletions .github/workflows/metal-run-microbenchmarks.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,8 @@ jobs:
PIPELINE_TYPE="microbenchmarks"
if [ "${{ matrix.runner-info.ccl }}" == "true" ]; then
PIPELINE_TYPE="ccl_microbenchmarks"
else
TT_METAL_SLOW_DISPATCH_MODE=1 ./tests/scripts/run_tunneler_tests.sh --machine-type ${{ matrix.runner-info.runs-on[0] }}
fi
./tests/scripts/run_tests.sh --tt-arch $ARCH_NAME --pipeline-type "$PIPELINE_TYPE"
- name: Upload microbenchmark report csvs
Expand Down
28 changes: 6 additions & 22 deletions .github/workflows/package-and-release.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -180,32 +180,16 @@ jobs:
infra/machine_setup/scripts/setup_hugepages.py
metal_libs-*+*.whl
fail_on_unmatched_files: true
create-docker-image:
create-docker-release-image:
needs: [
create-tag,
create-and-upload-draft-release
]
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to GitHub Container Registry
uses: docker/login-action@v3
with:
registry: https://ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Build and push
env:
TT_METAL_DOCKER_IMAGE: tt-metalium/ubuntu-20.04-amd64
uses: docker/build-push-action@v6
with:
push: true
tags: ghcr.io/${{ github.repository }}/tt-metalium/ubuntu-20.04-amd64:${{ needs.create-tag.outputs.version }}-dev
context: .
file: dockerfile/ubuntu-20.04-amd64.Dockerfile
uses: ./.github/workflows/publish-release-image.yaml
secrets: inherit
with:
version: ${{ needs.create-tag.outputs.version }}
is_major_version: ${{ needs.get-params.outputs.is-release-candidate !='true' && needs.get-params.outputs.should-create-release == 'true' }}
release-docs:
needs: [
get-params,
Expand Down
30 changes: 23 additions & 7 deletions .github/workflows/publish-release-image-wrapper.yaml
Original file line number Diff line number Diff line change
@@ -1,12 +1,28 @@
name: "Create and Publish Release Docker Image"

on:
workflow_call:
workflow_dispatch:

jobs:
to_be_filled_out:
steps:
- name: This workflow will be filled out in https://github.com/tenstorrent/tt-metal/pull/15013
run: |
echo "NOOP"
build-artifact:
uses: ./.github/workflows/build-artifact.yaml
secrets: inherit
build-wheels:
needs: build-artifact
strategy:
matrix:
# Since pre-compiled builds only run on 20.04, we can only test on 20.04 for now
# The full 22.04 flow can be tested without precompiled
os: [ubuntu-20.04]
arch: [grayskull, wormhole_b0]
uses: ./.github/workflows/_build-wheels-impl.yaml
with:
os: ${{ matrix.os }}
arch: ${{ matrix.arch }}
from-precompiled: true
publish-release-image:
needs: build-wheels
uses: ./.github/workflows/publish-release-image.yaml
secrets: inherit
with:
version: dev-${GITHUB_REF_NAME//\//-}
is_major_version: false
131 changes: 131 additions & 0 deletions .github/workflows/publish-release-image.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,131 @@
name: "[internal] Create and Publish Release Docker Image"

on:
workflow_call:
inputs:
version:
required: true
type: string
is_major_version:
required: true
type: boolean
default: false
timeout:
required: false
type: number
default: 10
jobs:
create-docker-release-image:
strategy:
matrix:
os: [ubuntu-20.04]
arch: [grayskull, wormhole_b0]
runs-on:
- build-docker
- in-service
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to GitHub Container Registry
uses: docker/login-action@v3
with:
registry: https://ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Download wheels
uses: actions/download-artifact@v4
with:
name: eager-dist-${{ matrix.os }}-${{ matrix.arch }}
- name: Get the name of the wheel and set up env variables
id: generate-tag-name
run: |
echo "WHEEL_FILENAME=$(ls -1 *.whl)" >> $GITHUB_ENV
REPO_IMAGE_NAME=ghcr.io/${{ github.repository }}/tt-metalium-${{ matrix.os }}-amd64-release/${{ matrix.arch }}
echo "REPO_IMAGE_NAME=$REPO_IMAGE_NAME" >> $GITHUB_ENV
TAG_NAME=$REPO_IMAGE_NAME:${{ inputs.version }}
echo "TAG_NAME=$TAG_NAME" >> $GITHUB_ENV
- name: Build and push
uses: docker/build-push-action@v6
with:
push: true
build-args: |
WHEEL_FILENAME=${{ env.WHEEL_FILENAME }}
BASE_IMAGE_NAME=tt-metalium/${{ matrix.os }}-amd64
tags: ${{ env.TAG_NAME }}
context: .
file: dockerfile/release.Dockerfile
smoke-test-docker-image:
needs: create-docker-release-image
strategy:
matrix:
os: [ubuntu-20.04]
test_group:
[
{
arch: grayskull,
runs-on: ["cloud-virtual-machine", "E150", "in-service"],
cmd: pytest tests/end_to_end_tests,
},
{
arch: wormhole_b0,
runs-on: ["cloud-virtual-machine", "N150", "in-service"],
cmd: pytest tests/end_to_end_tests,
},
{
arch: wormhole_b0,
runs-on: ["cloud-virtual-machine", "N300", "in-service"],
cmd: pytest tests/end_to_end_tests,
},
]
env:
ARCH_NAME: ${{ matrix.test_group.arch }}
LOGURU_LEVEL: INFO
runs-on: ${{ matrix.test_group.runs-on }}
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Run smoke test on the image
timeout-minutes: ${{ inputs.timeout }}
uses: ./.github/actions/docker-run
with:
docker_os_arch: tt-metalium-${{ matrix.os }}-amd64-release/${{ matrix.test_group.arch }}
docker_password: ${{ secrets.GITHUB_TOKEN }}
run_args: |
${{ matrix.test_group.cmd }}
tag-docker-image-as-latest:
needs: [smoke-test-docker-image, create-docker-release-image]
strategy:
matrix:
os: [ubuntu-20.04]
arch: [grayskull, wormhole_b0]
runs-on:
- build-docker
- in-service
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Docker login
uses: docker/login-action@v3
with:
registry: https://ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Tag latest if this is a major version release
run: |
set -eu # basic shell hygiene
LATEST_TAG=latest
if [ "${{ inputs.is_major_version }}" = "true" ]; then
LATEST_TAG=latest
else
LATEST_TAG=latest-rc
fi
echo "Determined that the current tag is " $LATEST_TAG
REPO_IMAGE_NAME=ghcr.io/${{ github.repository }}/tt-metalium-${{ matrix.os }}-amd64-release/${{ matrix.arch }}
TAG_NAME=$REPO_IMAGE_NAME:${{ inputs.version }}
docker pull $TAG_NAME
echo "Tagging the image as " $REPO_IMAGE_NAME:$LATEST_TAG
docker tag $TAG_NAME $REPO_IMAGE_NAME:$LATEST_TAG
echo "Pushing image with tag " $REPO_IMAGE_NAME:$LATEST_TAG
docker push $REPO_IMAGE_NAME:$LATEST_TAG
2 changes: 1 addition & 1 deletion .github/workflows/t3000-demo-tests-impl.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ jobs:
test-group: [
{ name: "t3k_falcon40b_tests", arch: wormhole_b0, cmd: run_t3000_falcon40b_tests, timeout: 50, owner_id: U053W15B6JF}, #Djordje Ivanovic
{ name: "t3k_llama3_tests", arch: wormhole_b0, cmd: run_t3000_llama3_tests, timeout: 30, owner_id: U03PUAKE719}, # Miguel Tairum
# { name: "t3k_llama3_vision_tests", arch: wormhole_b0, cmd: run_t3000_llama3_vision_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k_llama3_vision_tests", arch: wormhole_b0, cmd: run_t3000_llama3_vision_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k_llama3_70b_tests", arch: wormhole_b0, cmd: run_t3000_llama3_70b_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k_falcon7b_tests", arch: wormhole_b0, cmd: run_t3000_falcon7b_tests, timeout: 90, owner_id: U05RWH3QUPM}, #Salar Hosseini
{ name: "t3k_mixtral_tests", arch: wormhole_b0, cmd: run_t3000_mixtral_tests, timeout: 50, owner_id: U03PUAKE719}, # Miguel Tairum
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/t3000-frequent-tests-impl.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,8 @@ jobs:
{ name: "t3k ethernet tests", arch: wormhole_b0, cmd: run_t3000_ethernet_tests, timeout: 60, owner_id: ULMEPM2MA}, #Sean Nijjar
{ name: "t3k trace stress tests", arch: wormhole_b0, cmd: run_t3000_trace_stress_tests, timeout: 120, owner_id: U03NG0A5ND7}, #Aditya Saigal
{ name: "t3k falcon40b tests", arch: wormhole_b0, cmd: run_t3000_falcon40b_tests, timeout: 120, owner_id: U04S2UV6L8N}, #Sofija Jovic
# { name: "t3k llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
# { name: "t3k n300 mesh llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k n300 mesh llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k llama3 tests", arch: wormhole_b0, cmd: run_t3000_llama3_tests, timeout: 45, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
{ name: "t3k llama2_70b tests", arch: wormhole_b0, cmd: run_t3000_llama2_70b_tests, timeout: 45, owner_id: U03FJB5TM5Y}, #Colman Glagovich
# { name: "t3k llama3_70b tests", arch: wormhole_b0, cmd: run_t3000_llama3_70b_tests, timeout: 45, owner_id: U03FJB5TM5Y}, #Colman Glagovich # FIXME issue #14934
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/t3000-unit-tests-impl.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,8 @@ jobs:
{ name: "t3k falcon40b tests", arch: wormhole_b0, cmd: run_t3000_falcon40b_tests, timeout: 30, owner_id: U053W15B6JF}, #Djordje Ivanovic
{ name: "t3k llama3-small tests", arch: wormhole_b0, cmd: run_t3000_llama3-small_tests, timeout: 30, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
{ name: "t3k llama3.2-11b tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b_tests, timeout: 30, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
# { name: "t3k llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
# { name: "t3k n300 mesh llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k n300 mesh llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
{ name: "t3k llama3.1-70b tests", arch: wormhole_b0, cmd: run_t3000_llama3.1-70b_tests, timeout: 30, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
{ name: "t3k mixtral tests", arch: wormhole_b0, cmd: run_t3000_mixtral_tests, timeout: 30, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
{ name: "t3k grok tests", arch: wormhole_b0, cmd: run_t3000_grok_tests, timeout: 30, owner_id: U03HY7MK4BT}, #Mark O'Connor
Expand Down
23 changes: 0 additions & 23 deletions .github/workflows/test-comment.yaml

This file was deleted.

4 changes: 4 additions & 0 deletions .github/workflows/ttnn-run-sweeps.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -42,9 +42,11 @@ on:
- eltwise.unary.rsqrt.rsqrt_pytorch2
- eltwise.unary.rdiv.rdiv
- eltwise.unary.frac.frac
- eltwise.unary.frac.frac_sharded
- eltwise.unary.ceil.ceil
- eltwise.unary.ceil.ceil_pytorch2
- eltwise.unary.trunc.trunc
- eltwise.unary.trunc.trunc_sharded
- eltwise.unary.floor.floor
- eltwise.unary.floor.floor_pytorch2
- eltwise.unary.clone.clone
Expand Down Expand Up @@ -111,6 +113,7 @@ on:
- eltwise.unary.relu_max.relu_max
- eltwise.unary.softplus.softplus
- eltwise.unary.selu.selu
- eltwise.unary.softshrink.softshrink_sharded
- eltwise.unary_backward.fill_zero_bw
- eltwise.unary_backward.log_sigmoid_bw
- eltwise.unary_backward.logit_bw
Expand Down Expand Up @@ -180,6 +183,7 @@ on:
- eltwise.unary.mish.mish
- eltwise.unary.mish.mish_sharded
- eltwise.unary.multigammaln.multigammaln
- eltwise.unary.multigammaln.multigammaln_sharded
- eltwise.unary.isfinite.isfinite
- eltwise.unary.isfinite.isfinite_sharded
- eltwise.unary.isinf.isinf
Expand Down
2 changes: 2 additions & 0 deletions CODEOWNERS
Original file line number Diff line number Diff line change
Expand Up @@ -155,6 +155,8 @@ models/demos/t3000/mixtral8x7b @yieldthought @mtairum @uaydonat
models/demos/tg/llama3_70b @cglagovichTT @uaydonat @johanna-rock-tt @djordje-tt @kpaigwar
models/demos/tg/falcon7b @skhorasganiTT @djordje-tt @uaydonat
models/demos/grayskull @uaydonat
models/demos/yolov4 @dvartaniansTT @shwetankTT
models/demos/wormhole/yolov4 @dvartaniansTT @shwetankTT
models/demos/**/*resnet* @mywoodstock @shwetankTT @tt-aho
models/experimental/functional_unet @esmalTT @uaydonat @mywoodstock
models/perf/ @uaydonat
Expand Down
Loading

0 comments on commit 9b53818

Please sign in to comment.