[Bug] ChatQnA Benchmarking documentation doesnt cover Gaudi specific Kubernetes setup steps #793
Closed
1 of 6 tasks
Labels
Dev
documentation
Improvements or additions to documentation
Hacktoberfest
Kube
OPEAHack
Issue created for OPEA Hackathon
Comments
|
@amberjain1 Which file do you mean? |
|
@yongfengdu Is this something you will complete in October? If not, let's try to assign someone from the Hackathon |
I'm not covering the benchmarking part, feel free to assign someone else. |
wangkl2
pushed a commit
to wangkl2/GenAIExamples
that referenced
this issue
Dec 11, 2024
* graphRAG dataprep llama-index validated w openai endpoints Signed-off-by: rbrugaro <[email protected]> * llama-index graphRAG retrieval validated with openai models Signed-off-by: rbrugaro <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * validated code usng TGI/TEI instead of openai Signed-off-by: Rita Brugarolas <[email protected]> * compose.yaml for dataprep validated with neo4j, TGI/TEI, openai Signed-off-by: Rita Brugarolas <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * graphRAG retriever validated and full compose.yaml Signed-off-by: Rita Brugarolas <[email protected]> * minor fix Signed-off-by: Rita Brugarolas <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add graphRAGGateway WIP Signed-off-by: Rita Brugarolas <[email protected]> * graphragGateway working in E2E Example Signed-off-by: Rita Brugarolas <[email protected]> * fix schedule in orchestrator to support ChatCompletionRequest input Signed-off-by: Rita Brugarolas <[email protected]> * change default to TGI instead of openAI and add test code for neo4jretriever Signed-off-by: Rita Brugarolas <[email protected]> * test code for dataprep-neo4j microservice Signed-off-by: Rita Brugarolas <[email protected]> * improved READMES Signed-off-by: Rita Brugarolas <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update docker build path for tests Signed-off-by: Rita Brugarolas <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * minor fix Signed-off-by: Rita Brugarolas <[email protected]> * fix typo in container name Signed-off-by: Rita Brugarolas <[email protected]> * resolve image name conflict for hub publishing Signed-off-by: Rita Brugarolas <[email protected]> * add tgi validation to miicroservice tests Signed-off-by: Rita Brugarolas <[email protected]> * rename test script to trigger cicd correctly w hpu Signed-off-by: Rita Brugarolas <[email protected]> * rename test containers for cicd Signed-off-by: Rita Brugarolas <[email protected]> * update HF_TOKEN in TGI/TEI test scripts Signed-off-by: Rita Brugarolas <[email protected]> * swaped larger model so the graph isnt empty in ci test Signed-off-by: Rita Brugarolas <[email protected]> * set 4 hpu for 70B model in ci test Signed-off-by: Rita Brugarolas <[email protected]> * add extra time for large model loading cicd Signed-off-by: Rita Brugarolas <[email protected]> * fix tgi gaudi shard args Signed-off-by: Rita Brugarolas <[email protected]> * switch to chat cause chat template is needed Signed-off-by: Rita Brugarolas <[email protected]> * enable logs in test Signed-off-by: Rita Brugarolas <[email protected]> * use locally downloaded model in CI machine Signed-off-by: Rita Brugarolas <[email protected]> * use local model path and reduce wait time Signed-off-by: Rita Brugarolas <[email protected]> * clear ports before ci run Signed-off-by: Rita Brugarolas <[email protected]> * fix cache model access Signed-off-by: Rita Brugarolas <[email protected]> * fix cache model access Signed-off-by: Rita Brugarolas <[email protected]> * incrased wait time for tgi shards ready Signed-off-by: Rita Brugarolas <[email protected]> * wait until tgi connected Signed-off-by: Rita Brugarolas <[email protected]> * switch back to small model for testing Signed-off-by: Rita Brugarolas <[email protected]> * minor readability fixes Signed-off-by: Rita Brugarolas <[email protected]> * README fixes Signed-off-by: Rita Brugarolas <[email protected]> --------- Signed-off-by: rbrugaro <[email protected]> Signed-off-by: Rita Brugarolas <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
yinghu5
added a commit
that referenced
this issue
Jan 10, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Priority
Undecided
OS type
Ubuntu
Hardware type
Gaudi2
Installation method
Deploy method
Running nodes
Multiple Nodes
What's the version?
NA
Description
The documentation of ChatQnA does points to the steps to setup a fresh Kubernetes cluster, but it doesnt cover the Gaudi specific operator installations.
Reproduce steps
Steps not covered in the documentation
Raw log
No response
The text was updated successfully, but these errors were encountered: