lvliang-intel
7197286a14
Fix ChatQnA manifest default port issue ( #1033 )
...
Signed-off-by: lvliang-intel <liang1.lv@intel.com >
2024-10-30 11:52:04 +08:00
Yao Qing
2332d22950
[Codegen] Replace codegen default Model to Qwen/Qwen2.5-Coder-7B-Instruct. ( #1013 )
...
Signed-off-by: Yao, Qing <qing.yao@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-10-28 09:18:01 +08:00
Chun Tao
41955f65ad
Add a sample UI image for CodeGen's TGI monitoring ( #1009 )
...
Signed-off-by: Chun Tao <chun.tao@intel.com >
2024-10-23 14:38:12 +08:00
lvliang-intel
9438d392b4
Update README for some minor issues ( #1000 )
...
Signed-off-by: lvliang-intel <liang1.lv@intel.com >
2024-10-22 10:30:18 +08:00
chen, suyue
eeced9b31c
Enhance CI/CD image build ( #961 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-10-17 14:33:58 +08:00
lkk
088ab98f31
update examples accuracy ( #941 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-10-14 13:20:50 +08:00
Louie Tsai
12469c92d8
Update CodeGen README for its workflow ( #911 )
...
Signed-off-by: Tsai, Louie <louie.tsai@intel.com >
2024-10-10 08:47:56 -07:00
David Kinder
3e796ba73d
doc: fix missing references to README.md ( #860 )
...
Signed-off-by: David B. Kinder <david.b.kinder@intel.com >
2024-09-24 21:40:42 +08:00
lvliang-intel
3fb60608b3
Use official tei gaudi image and update tgi gaudi version ( #810 )
...
Signed-off-by: lvliang-intel <liang1.lv@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-23 17:52:56 +08:00
Letong Han
a09395e4a4
[Doc] Update CodeGen and Translation READMEs ( #847 )
...
Signed-off-by: letonghan <letong.han@intel.com >
2024-09-19 16:01:35 +08:00
lkk
f04f061f8c
move evaluation scripts ( #842 )
...
Co-authored-by: root <root@idc708073.jf.intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-19 15:59:13 +08:00
XinyaoWa
2f03a3a894
Align parameters for "max_token, repetition_penalty,presence_penalty,frequency_penalty" ( #726 )
...
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-19 14:15:25 +08:00
lvliang-intel
bceacdc804
Fix README issues ( #817 )
...
Signed-off-by: lvliang-intel <liang1.lv@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-18 09:50:17 +08:00
Jaswanth Karani
b84c98983d
Made cogen react ui to use runtime environment variables ( #807 )
...
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-14 09:27:14 +08:00
Malini Bhandaru
558ea3bb7f
adopted tech writing style ( #796 )
...
Signed-off-by: Malini Bhandaru <malini.bhandaru@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-13 09:42:59 +08:00
XinyaoWa
264759d85a
fix path bug for reorg ( #801 )
...
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com >
2024-09-12 17:52:06 +08:00
XinyaoWa
d2bab99835
refine readme for reorg ( #782 )
...
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-11 14:57:29 +08:00
Lianhao Lu
ff6f841ec0
README: fix broken links ( #781 )
...
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com >
2024-09-11 09:41:01 +08:00
XinyaoWa
d73129cbf0
Refactor folder to support different vendors ( #743 )
...
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com >
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-09-10 23:27:19 +08:00
Lianhao Lu
ba94e0130d
Add ui/nginx support in K8S manifest for ChatQnA/CodeGen/CodeTrans/Docsum ( #773 )
...
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com >
2024-09-10 16:30:14 +08:00
Lianhao Lu
0629696333
K8S manifest: Update ChatQnA/CodeGen/CodeTrans/DocSum
...
- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
to avoid requiring creating directory for cache model.
- Add chatqna-guardrails manifest files.
- Fix bug #752 introduced by PR #669
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com >
2024-09-06 16:09:42 +08:00
David Kinder
67394b88fa
doc: fix headings and indenting ( #748 )
...
* doc: fix headings and indenting
* only one H1 header (for title) is allowed
* fix indenting under ordered lists
Signed-off-by: David B. Kinder <david.b.kinder@intel.com >
2024-09-06 12:59:33 +08:00
Ying Chun Guo
2a6af6491a
update mount path in xeon k8s ( #696 )
...
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com >
2024-08-30 15:09:00 +08:00
Steve Zhang
f5f1e323bb
Revert the LLM model for kubernetes GMS ( #675 )
...
* revert the LLM model to meta-llama/CodeLlama-7b-hf
Signed-off-by: zhlsunshine <huailong.zhang@intel.com >
2024-08-30 13:54:42 +08:00
Yao Qing
814164dc4f
[Codegen] Refine readme to prompt users on how to change the model. ( #695 )
...
* [Codegen] Refine readme to prompt users on how to change the model.
Signed-off-by: Yao, Qing <qing.yao@intel.com >
* [Codegen] Add section Required Model.
Signed-off-by: Yao, Qing <qing.yao@intel.com >
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Signed-off-by: Yao, Qing <qing.yao@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-08-29 22:17:03 +08:00
Abolfazl Shahbazi
1874dfd148
Remove 'vim' from all Dockerfiles ( #663 )
...
Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com >
Co-authored-by: lvliang-intel <liang1.lv@intel.com >
2024-08-28 08:30:49 -07:00
Steve Zhang
4133757642
Change docs of kubernetes for curl commands in README ( #661 )
...
* change docs for curl commands in README.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com >
* The Namespace 'CT' is invalid.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com >
2024-08-27 19:36:37 +08:00
Dina Suehiro Jones
c25063f4bb
Minor fixes for CodeGen Xeon and Gaudi Kubernetes codegen.yaml and doc updates ( #613 )
...
* Minor fixes for CodeGen Xeon and Gaudi Kubernetes codegen.yaml and doc updates
Signed-off-by: dmsuehir <dina.s.jones@intel.com >
2024-08-23 16:04:57 +08:00
chen, suyue
dfaf47978d
optimize CI log format ( #648 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-08-22 15:08:59 +08:00
Kefei Zhang
06cb308611
change codegen tgi model ( #646 )
...
* change codegen tgi model
Signed-off-by: KfreeZ <kefei.zhang@intel.com >
2024-08-22 11:42:57 +08:00
chen, suyue
5d39506c5c
Add env params for chatqna xeon test ( #642 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-08-21 22:53:32 +08:00
Sihan Chen
6674832162
fix tgi xeon tag ( #641 )
2024-08-21 22:17:07 +08:00
Lianhao Lu
01c1b7504f
Update K8S manifest for ChatQnA/CodeGen/CodeTrans/DocSum
...
- Sync with docker-compose changes since v0.8 release
- Add K8S probes
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com >
2024-08-20 10:45:15 +08:00
lvliang-intel
b2771ad3f2
Using TGI official release docker image for intel cpu ( #581 )
...
Signed-off-by: lvliang-intel <liang1.lv@intel.com >
2024-08-18 17:17:44 +08:00
Ying Chun Guo
71363a6b9d
change microservice tags in CD workflow ( #612 )
...
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com >
2024-08-16 21:57:28 +08:00
chen, suyue
a6385bc6fd
Fix left issues in CI/CD structure refactor ( #599 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-08-16 00:22:24 +08:00
chen, suyue
c26d0f62b8
Enhance CI/CD infrastructure ( #593 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
Signed-off-by: Sun, Xuehao <xuehao.sun@intel.com >
2024-08-15 22:39:21 +08:00
Letong Han
88eeb0d7e6
Remove LangSmith from Examples ( #545 )
...
Signed-off-by: letonghan <letong.han@intel.com >
2024-08-08 09:14:38 +08:00
Dina Suehiro Jones
17b9676a3d
CodeGen README updates ( #534 )
...
Signed-off-by: dmsuehir <dina.s.jones@intel.com >
2024-08-06 22:30:39 -07:00
ZePan110
7dd9952f5e
Remove deprecated folder. ( #536 )
...
Signed-off-by: zepan <ze.pan@intel.com >
2024-08-07 10:26:23 +08:00
ZePan110
ac89855ff8
Fix code scan warning ( #473 )
...
Signed-off-by: zepan <ze.pan@intel.com >
2024-08-02 09:31:30 +08:00
David Kinder
33f83293d6
doc: fix CodeGen/README.md markdown ( #475 )
...
* fix multiple H1 headings
* edit use of please
* remove use of unnecessary HTML tags
Signed-off-by: David B. Kinder <david.b.kinder@intel.com >
Co-authored-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com >
2024-07-31 09:24:12 +08:00
chen, suyue
a2437e83e7
update compose.yaml fix the test issue ( #467 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-07-28 23:36:39 +08:00
chen, suyue
965c13c556
rename docker compose.yaml ( #446 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-07-26 20:03:36 +08:00
huiyan2021
8f9bcd4b3c
Update image reference url in readme ( #465 )
2024-07-26 17:34:48 +08:00
David Kinder
8d0c8fb949
doc: fix missing title H1 heading ( #458 )
...
Signed-off-by: David B. Kinder <david.b.kinder@intel.com >
Co-authored-by: Haihao Shen <haihao.shen@intel.com >
2024-07-26 09:32:54 +08:00
Jaswanth Karani
1b48e54a3d
code-gen-react-ui ( #417 )
...
* CodeGen: Manifest to deploy CodeGen with ReactUI into Kubernetes
Include manifest to deploy CodeGen pipeline with ReactUI into
Kubernetes. Include as well README file for the steps.
Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com >
* code-gen-react-ui
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* made changes as per PR suggestions
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* updated readme
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* update base image
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* updated codegn dockerfile react
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* updated wait time
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* updated as per PR comments
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* aded react ui in gaudi test file
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* fixed PR comments
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* added docker pull for text-generation-model
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
* removed unused files
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
---------
Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com >
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com >
Co-authored-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com >
2024-07-24 09:01:16 -07:00
WenjiaoYue
e371b1e9d4
Update REAME to be consistent with .env variables ( #452 )
...
* Update REAME to be consistent with .env variables
Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com >
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-07-24 15:34:11 +08:00
Lianhao Lu
6e797fae89
README for installing 4 worklods using helm chart ( #431 )
...
Add README to install the following workloads using helm chart:
- ChatQnA
- CodeGen
- CodeTrans
- DocSum
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com >
2024-07-24 09:46:03 +08:00
Steve Zhang
290a74fae9
Update all examples yaml files of GMC in GenAIExample ( #436 )
...
* Update all examples yaml files of GMC in GenAIExample.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com >
2024-07-23 16:40:51 +08:00