hf_text-generation-inference/.github/workflows/build.yaml

434 lines
18 KiB
YAML
Raw Normal View History

2023-01-31 12:14:05 -07:00
name: Build and push docker image to internal registry
on:
workflow_dispatch:
push:
branches:
- 'main'
tags:
- 'v*'
2023-01-31 12:14:05 -07:00
pull_request:
2023-03-23 11:01:30 -06:00
paths:
- ".github/workflows/build.yaml"
- "integration-tests/**"
2023-03-23 11:01:30 -06:00
- "server/**"
- "proto/**"
- "router/**"
- "launcher/**"
- "Cargo.lock"
- "rust-toolchain.toml"
- "Dockerfile"
2023-01-31 12:14:05 -07:00
branches:
- 'main'
jobs:
2023-05-15 07:53:08 -06:00
start-runner:
name: Start self-hosted EC2 runner
runs-on: ubuntu-latest
env:
AWS_REGION: us-east-1
Pali gemma modeling (#1895) This PR adds paligemma modeling code Blog post: https://huggingface.co/blog/paligemma Transformers PR: https://github.com/huggingface/transformers/pull/30814 install the latest changes and run with ```bash # get the weights # text-generation-server download-weights gv-hf/PaliGemma-base-224px-hf # run TGI text-generation-launcher --model-id gv-hf/PaliGemma-base-224px-hf ``` basic example sending various requests ```python from huggingface_hub import InferenceClient client = InferenceClient("http://127.0.0.1:3000") images = [ "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/cow_beach_1.png", "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png", ] prompts = [ "What animal is in this image?", "Name three colors in this image.", "What are 10 colors in this image?", "Where is the cow standing?", "answer en Where is the cow standing?", "Is there a bird in the image?", "Is ther a cow in the image?", "Is there a rabbit in the image?", "how many birds are in the image?", "how many rabbits are in the image?", ] for img in images: print(f"\nImage: {img.split('/')[-1]}") for prompt in prompts: inputs = f"![]({img}){prompt}\n" json_data = { "inputs": inputs, "parameters": { "max_new_tokens": 30, "do_sample": False, }, } generated_output = client.text_generation(prompt, max_new_tokens=30, stream=False) print([f"{prompt}\n{generated_output}"]) ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-05-15 22:58:47 -06:00
EC2_AMI_ID: ami-0789b6925c11b1fb2
2023-05-15 07:53:08 -06:00
EC2_INSTANCE_TYPE: g5.12xlarge
EC2_SUBNET_ID: subnet-931b34f5,subnet-ecb993cd,subnet-943dc2d8,subnet-45371f1a,subnet-ee93e0df,subnet-fddc3dfc
EC2_SECURITY_GROUP: sg-030175c435ac141d6
2023-05-15 07:53:08 -06:00
outputs:
label: ${{ steps.start-ec2-runner.outputs.label }}
ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
steps:
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v1
with:
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
aws-region: ${{ env.AWS_REGION }}
- name: Start EC2 runner
id: start-ec2-runner
uses: philschmid/philschmid-ec2-github-runner@main
with:
mode: start
github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
ec2-image-id: ${{ env.EC2_AMI_ID }}
ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
subnet-id: ${{ env.EC2_SUBNET_ID }}
security-group-id: ${{ env.EC2_SECURITY_GROUP }}
aws-resource-tags: > # optional, requires additional permissions
[
{"Key": "Name", "Value": "ec2-tgi-github-runner"},
{"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
]
2023-01-31 12:14:05 -07:00
build-and-push-image:
2023-05-15 15:36:30 -06:00
concurrency:
group: ${{ github.workflow }}-build-and-push-image-${{ github.head_ref || github.run_id }}
2023-05-15 15:36:30 -06:00
cancel-in-progress: true
2023-05-15 07:53:08 -06:00
needs: start-runner # required to start the main job when the runner is ready
runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
permissions:
2023-04-13 08:23:47 -06:00
contents: write
packages: write
# This is used to complete the identity challenge
# with sigstore/fulcio when running outside of PRs.
id-token: write
2023-04-13 08:32:37 -06:00
security-events: write
2023-01-31 12:14:05 -07:00
steps:
- name: Checkout repository
uses: actions/checkout@v3
2023-03-03 07:07:27 -07:00
- name: Initialize Docker Buildx
uses: docker/setup-buildx-action@v2.0.0
with:
install: true
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1
2023-01-31 12:14:05 -07:00
- name: Tailscale
2023-05-15 07:53:08 -06:00
uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
2023-01-31 12:14:05 -07:00
with:
authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
- name: Login to GitHub Container Registry
if: github.event_name != 'pull_request'
2023-01-31 12:14:05 -07:00
uses: docker/login-action@v2
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to internal Container Registry
uses: docker/login-action@v2.1.0
with:
username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
registry: registry.internal.huggingface.tech
2023-02-06 06:33:56 -07:00
- name: Login to Azure Container Registry
if: github.event_name != 'pull_request'
2023-02-06 06:33:56 -07:00
uses: docker/login-action@v2.1.0
with:
username: ${{ secrets.AZURE_DOCKER_USERNAME }}
password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
2023-05-15 15:36:30 -06:00
# If pull request
2023-01-31 12:14:05 -07:00
- name: Extract metadata (tags, labels) for Docker
2023-05-15 15:36:30 -06:00
if: ${{ github.event_name == 'pull_request' }}
id: meta-pr
uses: docker/metadata-action@v4.3.0
with:
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
tags: |
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
# If main, release or tag
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name != 'pull_request' }}
2023-01-31 12:14:05 -07:00
id: meta
uses: docker/metadata-action@v4.3.0
with:
flavor: |
latest=auto
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
ghcr.io/huggingface/text-generation-inference
2023-02-06 06:33:56 -07:00
db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
2023-01-31 12:14:05 -07:00
tags: |
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
2023-01-31 12:14:05 -07:00
type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
- name: Build and push Docker image
id: build-and-push
uses: docker/build-push-action@v4
2023-01-31 12:14:05 -07:00
with:
context: .
file: Dockerfile
2023-05-15 15:36:30 -06:00
push: true
2023-01-31 12:14:05 -07:00
platforms: 'linux/amd64'
build-args: |
GIT_SHA=${{ env.GITHUB_SHA }}
2023-05-02 07:43:19 -06:00
DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}
2023-05-15 15:36:30 -06:00
tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
2023-05-23 09:42:19 -06:00
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
integration-tests:
concurrency:
group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
needs:
- start-runner
- build-and-push-image # Wait for the docker image to be built
runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
env:
DOCKER_VOLUME: /cache
steps:
- uses: actions/checkout@v2
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: 3.9
- name: Tailscale
uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
with:
authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
- name: Prepare disks
run: |
sudo mkfs -t ext4 /dev/nvme1n1
sudo mkdir ${{ env.DOCKER_VOLUME }}
sudo mount /dev/nvme1n1 ${{ env.DOCKER_VOLUME }}
- name: Install
run: |
make install-integration-tests
- name: Run tests
run: |
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}
export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
pytest -s -vv integration-tests
build-and-push-image-rocm:
concurrency:
group: ${{ github.workflow }}-build-and-push-image-rocm-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
needs:
- start-runner
- build-and-push-image # Wait for the main docker image to be built
- integration-tests # Wait for the main integration-tests
runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
permissions:
contents: write
packages: write
# This is used to complete the identity challenge
# with sigstore/fulcio when running outside of PRs.
id-token: write
security-events: write
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Initialize Docker Buildx
uses: docker/setup-buildx-action@v2.0.0
with:
install: true
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1
- name: Tailscale
uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
with:
authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
- name: Login to GitHub Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v2
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to internal Container Registry
uses: docker/login-action@v2.1.0
with:
username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
registry: registry.internal.huggingface.tech
- name: Login to Azure Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v2.1.0
with:
username: ${{ secrets.AZURE_DOCKER_USERNAME }}
password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
# If pull request
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name == 'pull_request' }}
id: meta-pr
uses: docker/metadata-action@v4.3.0
with:
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
tags: |
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
# If main, release or tag
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name != 'pull_request' }}
id: meta
uses: docker/metadata-action@v4.3.0
with:
flavor: |
latest=false
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
ghcr.io/huggingface/text-generation-inference
db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
tags: |
type=semver,pattern={{version}}-rocm
type=semver,pattern={{major}}.{{minor}}-rocm
type=raw,value=latest-rocm,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
- name: Build and push Docker image
id: build-and-push
uses: docker/build-push-action@v4
with:
context: .
file: Dockerfile_amd
push: true
platforms: 'linux/amd64'
build-args: |
GIT_SHA=${{ env.GITHUB_SHA }}
DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min
add intel xpu support for TGI (#1475) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil --> --------- Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> Co-authored-by: Morgan Funtowicz <funtowiczmo@gmail.com> Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-04-26 07:48:58 -06:00
build-and-push-image-intel:
concurrency:
group: ${{ github.workflow }}-build-and-push-image-intel-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
needs:
- start-runner
- build-and-push-image # Wait for the main docker image to be built
- integration-tests # Wait for the main integration-tests
runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
permissions:
contents: write
packages: write
# This is used to complete the identity challenge
# with sigstore/fulcio when running outside of PRs.
id-token: write
security-events: write
MI300 compatibility (#1764) Adds support for AMD Instinct MI300 in TGI. Most changes are: * Support PyTorch TunableOp to pick the GEMM/GEMV kernels for decoding https://github.com/pytorch/pytorch/tree/main/aten/src/ATen/cuda/tunable. TunableOp is disabled by default, and can be enabled with `PYTORCH_TUNABLEOP_ENABLED=1`. * Update ROCm dockerfile to PyTorch 2.3 (actually patched with changes from https://github.com/pytorch/pytorch/pull/124362) * Support SILU & Linear custom kernels contributed by AMD * Update vLLM paged attention to https://github.com/fxmarty/rocm-vllm/, branching out of a much more recent commit https://github.com/ROCm/vllm/commit/3489ce7936c5de588916ae3047c44c23c0b0c308 * Support FA2 Triton kernel as recommended by AMD. Can be used by specifying `ROCM_USE_FLASH_ATTN_V2_TRITON=1`. * Update dockerfile to ROCm 6.1 By default, TunableOp tuning results are saved in `/data` (e.g. `/data/tunableop_meta-llama-Llama-2-70b-chat-hf_tp1_rank0.csv`) in order to avoid to have to rerun the tuning at each `docker run`. Example: ``` Validator,PT_VERSION,2.3.0 Validator,ROCM_VERSION,6.1.0.0-82-5fabb4c Validator,HIPBLASLT_VERSION,0.7.0-1549b021 Validator,GCN_ARCH_NAME,gfx942:sramecc+:xnack- Validator,ROCBLAS_VERSION,4.1.0-cefa4a9b-dirty GemmTunableOp_Half_TN,tn_8192_7_28672,Gemm_Rocblas_45475,0.132098 GemmTunableOp_Half_TN,tn_10240_4_8192,Gemm_Rocblas_45546,0.0484431 GemmTunableOp_Half_TN,tn_32000_6_8192,Default,0.149546 GemmTunableOp_Half_TN,tn_32000_3_8192,Gemm_Rocblas_45520,0.147119 GemmTunableOp_Half_TN,tn_8192_3_28672,Gemm_Rocblas_45475,0.132645 GemmTunableOp_Half_TN,tn_10240_3_8192,Gemm_Rocblas_45546,0.0482971 GemmTunableOp_Half_TN,tn_57344_5_8192,Gemm_Rocblas_45520,0.255694 GemmTunableOp_Half_TN,tn_10240_7_8192,Gemm_Rocblas_45517,0.0482522 GemmTunableOp_Half_TN,tn_8192_3_8192,Gemm_Rocblas_45546,0.0444671 GemmTunableOp_Half_TN,tn_8192_5_8192,Gemm_Rocblas_45546,0.0445834 GemmTunableOp_Half_TN,tn_57344_7_8192,Gemm_Rocblas_45520,0.25622 GemmTunableOp_Half_TN,tn_8192_2_28672,Gemm_Rocblas_45475,0.132122 GemmTunableOp_Half_TN,tn_8192_4_8192,Gemm_Rocblas_45517,0.0453191 GemmTunableOp_Half_TN,tn_10240_5_8192,Gemm_Rocblas_45517,0.0482514 GemmTunableOp_Half_TN,tn_8192_5_28672,Gemm_Rocblas_45542,0.133914 GemmTunableOp_Half_TN,tn_8192_2_8192,Gemm_Rocblas_45517,0.0446516 GemmTunableOp_Half_TN,tn_8192_1_28672,Gemm_Hipblaslt_TN_10814,0.131953 GemmTunableOp_Half_TN,tn_10240_2_8192,Gemm_Rocblas_45546,0.0481043 GemmTunableOp_Half_TN,tn_32000_4_8192,Gemm_Rocblas_45520,0.147497 GemmTunableOp_Half_TN,tn_8192_6_28672,Gemm_Rocblas_45529,0.134895 GemmTunableOp_Half_TN,tn_57344_2_8192,Gemm_Rocblas_45520,0.254716 GemmTunableOp_Half_TN,tn_57344_4_8192,Gemm_Rocblas_45520,0.255731 GemmTunableOp_Half_TN,tn_10240_6_8192,Gemm_Rocblas_45517,0.0484816 GemmTunableOp_Half_TN,tn_57344_3_8192,Gemm_Rocblas_45520,0.254701 GemmTunableOp_Half_TN,tn_8192_4_28672,Gemm_Rocblas_45475,0.132159 GemmTunableOp_Half_TN,tn_32000_2_8192,Default,0.147524 GemmTunableOp_Half_TN,tn_32000_5_8192,Default,0.147074 GemmTunableOp_Half_TN,tn_8192_6_8192,Gemm_Rocblas_45546,0.0454045 GemmTunableOp_Half_TN,tn_57344_6_8192,Gemm_Rocblas_45520,0.255582 GemmTunableOp_Half_TN,tn_32000_7_8192,Default,0.146705 GemmTunableOp_Half_TN,tn_8192_7_8192,Gemm_Rocblas_45546,0.0445489 ``` --------- Co-authored-by: Mohit Sharma <mohit21sharma.ms@gmail.com>
2024-05-17 07:30:47 -06:00
outputs:
# env is not available in the later `container:`, but previous job outputs are.
short_sha: ${{ env.GITHUB_SHA_SHORT }}
add intel xpu support for TGI (#1475) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil --> --------- Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> Co-authored-by: Morgan Funtowicz <funtowiczmo@gmail.com> Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-04-26 07:48:58 -06:00
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Initialize Docker Buildx
uses: docker/setup-buildx-action@v2.0.0
with:
install: true
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1
- name: Tailscale
uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
with:
authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
- name: Login to GitHub Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v2
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to internal Container Registry
uses: docker/login-action@v2.1.0
with:
username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
registry: registry.internal.huggingface.tech
- name: Login to Azure Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v2.1.0
with:
username: ${{ secrets.AZURE_DOCKER_USERNAME }}
password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
# If pull request
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name == 'pull_request' }}
id: meta-pr
uses: docker/metadata-action@v4.3.0
with:
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
tags: |
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel
# If main, release or tag
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name != 'pull_request' }}
id: meta
uses: docker/metadata-action@v4.3.0
with:
flavor: |
latest=false
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
ghcr.io/huggingface/text-generation-inference
db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
tags: |
type=semver,pattern={{version}}-intel
type=semver,pattern={{major}}.{{minor}}-intel
type=raw,value=latest-intel,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel
- name: Build and push Docker image
id: build-and-push
uses: docker/build-push-action@v4
with:
context: .
file: Dockerfile_intel
push: true
platforms: 'linux/amd64'
build-args: |
GIT_SHA=${{ env.GITHUB_SHA }}
DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-intel
tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min
2023-05-15 07:53:08 -06:00
stop-runner:
name: Stop self-hosted EC2 runner
needs:
2023-05-15 07:53:08 -06:00
- start-runner
- build-and-push-image
- build-and-push-image-rocm
add intel xpu support for TGI (#1475) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil --> --------- Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> Co-authored-by: Morgan Funtowicz <funtowiczmo@gmail.com> Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-04-26 07:48:58 -06:00
- build-and-push-image-intel
2023-05-15 15:36:30 -06:00
- integration-tests
runs-on: ubuntu-latest
2023-05-15 07:53:08 -06:00
env:
AWS_REGION: us-east-1
if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
steps:
2023-05-15 07:53:08 -06:00
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v1
with:
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
aws-region: ${{ env.AWS_REGION }}
- name: Stop EC2 runner
uses: philschmid/philschmid-ec2-github-runner@main
with:
mode: stop
github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
label: ${{ needs.start-runner.outputs.label }}
ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}
MI300 compatibility (#1764) Adds support for AMD Instinct MI300 in TGI. Most changes are: * Support PyTorch TunableOp to pick the GEMM/GEMV kernels for decoding https://github.com/pytorch/pytorch/tree/main/aten/src/ATen/cuda/tunable. TunableOp is disabled by default, and can be enabled with `PYTORCH_TUNABLEOP_ENABLED=1`. * Update ROCm dockerfile to PyTorch 2.3 (actually patched with changes from https://github.com/pytorch/pytorch/pull/124362) * Support SILU & Linear custom kernels contributed by AMD * Update vLLM paged attention to https://github.com/fxmarty/rocm-vllm/, branching out of a much more recent commit https://github.com/ROCm/vllm/commit/3489ce7936c5de588916ae3047c44c23c0b0c308 * Support FA2 Triton kernel as recommended by AMD. Can be used by specifying `ROCM_USE_FLASH_ATTN_V2_TRITON=1`. * Update dockerfile to ROCm 6.1 By default, TunableOp tuning results are saved in `/data` (e.g. `/data/tunableop_meta-llama-Llama-2-70b-chat-hf_tp1_rank0.csv`) in order to avoid to have to rerun the tuning at each `docker run`. Example: ``` Validator,PT_VERSION,2.3.0 Validator,ROCM_VERSION,6.1.0.0-82-5fabb4c Validator,HIPBLASLT_VERSION,0.7.0-1549b021 Validator,GCN_ARCH_NAME,gfx942:sramecc+:xnack- Validator,ROCBLAS_VERSION,4.1.0-cefa4a9b-dirty GemmTunableOp_Half_TN,tn_8192_7_28672,Gemm_Rocblas_45475,0.132098 GemmTunableOp_Half_TN,tn_10240_4_8192,Gemm_Rocblas_45546,0.0484431 GemmTunableOp_Half_TN,tn_32000_6_8192,Default,0.149546 GemmTunableOp_Half_TN,tn_32000_3_8192,Gemm_Rocblas_45520,0.147119 GemmTunableOp_Half_TN,tn_8192_3_28672,Gemm_Rocblas_45475,0.132645 GemmTunableOp_Half_TN,tn_10240_3_8192,Gemm_Rocblas_45546,0.0482971 GemmTunableOp_Half_TN,tn_57344_5_8192,Gemm_Rocblas_45520,0.255694 GemmTunableOp_Half_TN,tn_10240_7_8192,Gemm_Rocblas_45517,0.0482522 GemmTunableOp_Half_TN,tn_8192_3_8192,Gemm_Rocblas_45546,0.0444671 GemmTunableOp_Half_TN,tn_8192_5_8192,Gemm_Rocblas_45546,0.0445834 GemmTunableOp_Half_TN,tn_57344_7_8192,Gemm_Rocblas_45520,0.25622 GemmTunableOp_Half_TN,tn_8192_2_28672,Gemm_Rocblas_45475,0.132122 GemmTunableOp_Half_TN,tn_8192_4_8192,Gemm_Rocblas_45517,0.0453191 GemmTunableOp_Half_TN,tn_10240_5_8192,Gemm_Rocblas_45517,0.0482514 GemmTunableOp_Half_TN,tn_8192_5_28672,Gemm_Rocblas_45542,0.133914 GemmTunableOp_Half_TN,tn_8192_2_8192,Gemm_Rocblas_45517,0.0446516 GemmTunableOp_Half_TN,tn_8192_1_28672,Gemm_Hipblaslt_TN_10814,0.131953 GemmTunableOp_Half_TN,tn_10240_2_8192,Gemm_Rocblas_45546,0.0481043 GemmTunableOp_Half_TN,tn_32000_4_8192,Gemm_Rocblas_45520,0.147497 GemmTunableOp_Half_TN,tn_8192_6_28672,Gemm_Rocblas_45529,0.134895 GemmTunableOp_Half_TN,tn_57344_2_8192,Gemm_Rocblas_45520,0.254716 GemmTunableOp_Half_TN,tn_57344_4_8192,Gemm_Rocblas_45520,0.255731 GemmTunableOp_Half_TN,tn_10240_6_8192,Gemm_Rocblas_45517,0.0484816 GemmTunableOp_Half_TN,tn_57344_3_8192,Gemm_Rocblas_45520,0.254701 GemmTunableOp_Half_TN,tn_8192_4_28672,Gemm_Rocblas_45475,0.132159 GemmTunableOp_Half_TN,tn_32000_2_8192,Default,0.147524 GemmTunableOp_Half_TN,tn_32000_5_8192,Default,0.147074 GemmTunableOp_Half_TN,tn_8192_6_8192,Gemm_Rocblas_45546,0.0454045 GemmTunableOp_Half_TN,tn_57344_6_8192,Gemm_Rocblas_45520,0.255582 GemmTunableOp_Half_TN,tn_32000_7_8192,Default,0.146705 GemmTunableOp_Half_TN,tn_8192_7_8192,Gemm_Rocblas_45546,0.0445489 ``` --------- Co-authored-by: Mohit Sharma <mohit21sharma.ms@gmail.com>
2024-05-17 07:30:47 -06:00
# TODO: Move this to `build_amd.yml` (and `build_nvidia.yml`)
# integration-tests-rocm:
# concurrency:
# group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
# cancel-in-progress: true
# needs:
# - start-runner
# - build-and-push-image
# - integration-tests
# - build-and-push-image-rocm
# - stop-runner
# runs-on: [self-hosted, amd-gpu, multi-gpu, mi300]
# container:
# image: registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ needs.build-and-push-image-rocm.outputs.short_sha }}-rocm
# options: --device /dev/kfd --device /dev/dri --env ROCR_VISIBLE_DEVICES --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/cache
# env:
# DOCKER_VOLUME: /cache
# steps:
# - name: ROCM-SMI
# run: |
# rocm-smi
# - name: ROCM-INFO
# run: |
# rocminfo | grep "Agent" -A 14
# - name: Show ROCR environment
# run: |
# echo "ROCR: $ROCR_VISIBLE_DEVICES"
# - name: Install
# run: |
# make install-integration-tests
# - name: Run tests
# run: |
# export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
# pytest -s -vv integration-tests