Commit Graph

336 Commits

Author SHA1 Message Date
Zhenzhong1
5158b5e822 updateto vllm images 2024-10-29 02:44:27 -07:00
Zhenzhong1
1c3f55602a added vllm 2024-10-29 02:13:06 -07:00
Zhenzhong1
bb4c1dbc44 Update configmap.yaml 2024-10-28 19:36:32 +08:00
Zhenzhong1
16018085b0 added some envs 2024-10-25 09:22:36 +03:00
Zhenzhong1
93bbd5131f updated oob manifests 2024-10-24 05:11:23 +03:00
chensuyue
4f32f867ec update cpu core into 80
Signed-off-by: chensuyue <suyue.chen@intel.com>
2024-10-23 14:49:04 +08:00
Zhenzhong1
1046aad26f removed benchmark template 2024-10-23 09:30:03 +03:00
pre-commit-ci[bot]
2876677214 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2024-10-22 09:11:46 +00:00
Zhenzhong1
a9536321a0 added the tuned tgi params 2024-10-22 12:11:22 +03:00
pre-commit-ci[bot]
065222f29b [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2024-10-22 08:19:15 +00:00
Zhenzhong1
3f596d9747 update README 2024-10-22 11:18:49 +03:00
Zhenzhong1
b9c646a2b8 update README 2024-10-22 11:09:50 +03:00
Zhenzhong1
f3cbcadfa2 fixed visualqna image issues & tgi params issues 2024-10-22 10:26:44 +03:00
Zhenzhong1
e21ee76f24 updated tgiparams 2024-10-22 09:15:11 +03:00
pre-commit-ci[bot]
8effe7a4eb [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2024-10-22 05:38:44 +00:00
Zhenzhong1
0d3876d6fa removed multiple yamls 2024-10-22 08:38:15 +03:00
Zhenzhong1
bb46f5b355 added visual qna & update deployment template 2024-10-22 05:45:00 +03:00
Zhenzhong1
bcaffd7db4 added more cases 2024-10-21 12:21:02 +03:00
Zhenzhong1
124143ea40 removed values.yaml 2024-10-21 12:10:59 +03:00
Zhenzhong1
6dc4bb5c79 refactoered image 2024-10-21 11:54:18 +03:00
Zhenzhong Xu
048b4e1df9 refactored AudioQNA 2024-10-21 11:06:37 +03:00
Zhenzhong Xu
58ff7d9518 moved HUGGINGFACEHUB_API_TOKEN 2024-10-21 10:41:20 +03:00
Zhenzhong Xu
9ee1a7410b rename 2024-10-21 10:31:27 +03:00
Zhenzhong Xu
24166615d7 removed spec 2024-10-21 09:01:00 +03:00
Zhenzhong Xu
a0b2263fd3 updated customize deployment template 2024-10-21 08:49:38 +03:00
Zhenzhong Xu
5c2f3f0301 move image & replicas path 2024-10-21 07:04:31 +03:00
Zhenzhong Xu
a70775d3d6 updated chatqna helmcharts image name 2024-10-21 06:54:27 +03:00
Zhenzhong Xu
3dd5475773 updated chatqna helmcharts 2024-10-21 06:40:46 +03:00
Zhenzhong1
d6b04b3405 benchmark helmcharts (#995)
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-10-21 11:13:24 +08:00
lvliang-intel
3c164f3aa2 Make rerank run on gaudi for hpu docker compose (#980)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-10-18 21:49:36 +08:00
CharleneHu-42
7669c42085 Update ChatQnA README to add benchmark launcher (#958)
Signed-off-by: CharleneHu-42 <yabai.hu@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Yi Yao <yi.a.yao@intel.com>
2024-10-18 13:33:20 +08:00
lvliang-intel
256b58c07e Replace environment variables with service name for ChatQnA (#977)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-10-18 11:31:24 +08:00
ylg
37c74b232c Update ChatQnA yaml and set retriever's TEI_EMBEDDING_ENDPOINT (#953)
Signed-off-by: longguang.yue <bigclouds@163.com>
2024-10-17 16:58:47 +08:00
Sihan Chen
4a265abb73 Fix top_n rerank docs (#976) 2024-10-17 15:49:16 +08:00
Sihan Chen
b0487fe92b fix chatqna accuracy issue with incorrect penalty (#974) 2024-10-17 15:48:44 +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
WenjiaoYue
b377c2b8f8 Update manifest ui containerPort (#952)
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>
2024-10-17 09:42:55 +08:00
lvliang-intel
c930bea172 Add missing nginx microservice and fix frontend test (#951)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-10-16 13:29:31 +08:00
lvliang-intel
778afb50ac Clean no wrapper image in performance benchmark manifests (#955)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-10-15 18:21:53 +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
xiguiw
b056ce6617 [Doc] Update ChatQnA AIPC README (#935)
Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-10-12 11:04:53 +08:00
xiguiw
773c32b38b Fix AIPC retriever and UI error (#933)
Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
2024-10-11 13:35:27 +08:00
lvliang-intel
619d941047 Set no wrapper ChatQnA as default (#891)
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>
2024-10-11 13:30:45 +08:00
Abolfazl Shahbazi
b71a12d424 Remove 'vim' from Dockerfiles (#924)
Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com>
2024-10-10 18:24:31 -07:00
feng-intel
ae10712fe8 doc: Update ChatQnA/benchmark/performance doc (#930) 2024-10-10 16:30:40 +08:00
pallavijaini0525
e2f9037344 Added the K8s yaml for vLLM support (#917)
Signed-off-by: desaidhr <dhruv.desai@intel.com>
Co-authored-by: desaidhr <dhruv.desai@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-10-10 11:08:07 +08:00
Zhenzhong1
d16c80e493 [ChatQnA] manage your own ChatQnA pipelines. (#878)
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-09-30 17:01:44 +09:00
sri-intel
2de1bfc5bb Bug fix for issue #881 (#882)
Signed-off-by: srinarayan-srikanthan <srinarayan.srikanthan@intel.com>
2024-09-27 13:06:02 +08:00
sri-intel
75df2c9979 docker install instruction for csp (#843)
Signed-off-by: sri <srinarayan.srikanthan@intel.com>
Signed-off-by: srinarayan-srikanthan <srinarayan.srikanthan@intel.com>
2024-09-27 13:00:10 +08:00
jotpalch
bd32b03e3c Doc: Update folder path to correct location in "Deploy ChatQnA in Kubernetes" (#875) 2024-09-26 14:38:22 +08:00