xiaohei/model_garden
1
0
Fork 0
mirror of https://github.com/GoogleCloudPlatform/vertex-ai-samples.git synced 2026-09-26 14:42:04 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,288 Commits 1,765 Branches 0 Tags
8976c57b9c37ae3edc3b939bb24293eb71e560f9
Commit Graph
39 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Dustin LuongandCopybara-Service 8976c57b9c Update the Kimi-K3 deployment notebook image URI. 
PiperOrigin-RevId: 964692807
 2026-08-14 07:39:13 -07:00
Dustin LuongandCopybara-Service 37a85d53f4 No public description 
MG_DOCKER_CODES_PIPER_ORIGIN_REV_ID: 958290655
 2026-08-03 04:07:45 -07:00
Dustin LuongandCopybara-Service 0b0e362ab9 Add Kimi K3 Model Garden deployment notebook 
PiperOrigin-RevId: 958290655
 2026-08-03 04:06:44 -07:00
Dustin LuongandCopybara-Service 57ee4e2eab Update Qwen3 deployment notebook with new variants and corrected model names. 
PiperOrigin-RevId: 794407429
 2025-08-12 22:41:45 -07:00
Dustin LuongandCopybara-Service 4d736d7992 Use correct notebook_util. 
PiperOrigin-RevId: 794396544
 2025-08-12 22:00:22 -07:00
Dustin LuongandCopybara-Service 69e92a650d Add gpt-oss-20b finetuning with lora on Vertex notebook. 
PiperOrigin-RevId: 794317611
 2025-08-12 16:57:36 -07:00
Dustin LuongandCopybara-Service 31ca3e36f4 Add Qwen3-30B-A3B instruct and thinking 2507 variants to notebook. 
PiperOrigin-RevId: 791746627
 2025-08-06 10:27:39 -07:00
Dustin LuongandCopybara-Service c8b53a614e Fix text in TEI notebook to change instances of nomic-ai/nomic-embed-text-v1 to Qwen/Qwen3-Embedding-8B. 
PiperOrigin-RevId: 789204281
 2025-07-30 23:26:39 -07:00
Dustin LuongandCopybara-Service fc8e9e4483 Set Qwen/Qwen3-Embedding-8B as example model in TEI notebook. 
PiperOrigin-RevId: 788960826
 2025-07-30 10:48:47 -07:00
Dustin LuongandCopybara-Service 01d513eea3 Update the deployment notebook for Qwen3 models to include Qwen3-235B-Thinking-2507 and Qwen3-235B-Thinking-2507-FP8. 
PiperOrigin-RevId: 788636454
 2025-07-29 15:45:43 -07:00
Dustin LuongandCopybara-Service ffb5ea7e88 Update HF TEI serving image to use new, FEDRamp compliant container. 
PiperOrigin-RevId: 788203719
 2025-07-28 16:36:17 -07:00
Dustin LuongandCopybara-Service 44a63c8186 Add Qwen3-235B-A22B-Instruct-2507 models to Qwen3 deployment notebook. 
PiperOrigin-RevId: 786375387
 2025-07-23 12:12:28 -07:00
Dustin LuongandCopybara-Service 0ff91f926d Update SAM notebook to use new container that is FedRamp compliant. 
PiperOrigin-RevId: 782652376
 2025-07-13 14:06:26 -07:00
Dustin LuongandCopybara-Service 7ed8313d37 Add link to timesfm serving docker source code. 
PiperOrigin-RevId: 781718474
 2025-07-10 15:59:44 -07:00
Dustin LuongandCopybara-Service 7eb8b76d19 Remove reference server deployment and inference from llama3.2 notebook. 
PiperOrigin-RevId: 757455670
 2025-05-11 11:01:47 -07:00
Dustin LuongandCopybara-Service 4c4e224d31 Update Qwen3 deployment notebook with FP8 support. 
PiperOrigin-RevId: 756041267
 2025-05-07 15:59:11 -07:00
Dustin LuongandCopybara-Service 68960f1221 Add SDK deploy option to Qwen3 deployment notebook. 
PiperOrigin-RevId: 753636431
 2025-05-01 10:17:08 -07:00
Dustin LuongandCopybara-Service ecd1fc28d2 Set model id to GCS bucket for Qwen3 235B model for better stability. 
PiperOrigin-RevId: 753430192
 2025-04-30 21:33:20 -07:00
Dustin LuongandCopybara-Service e851c1ad99 Upload Qwen3 deployment notebook. 
PiperOrigin-RevId: 753265446
 2025-04-30 12:19:21 -07:00
Dustin LuongandCopybara-Service c4b3f39bfe Remove raw_response field from request. Also fix chat completions format. 
PiperOrigin-RevId: 740023921
 2025-03-24 12:04:56 -07:00
Dustin LuongandCopybara-Service dc59488638 Add YaRN scaling to QwQ deployment notebook for 128k context length. Fix chatCompletions format. 
PiperOrigin-RevId: 738871259
 2025-03-20 11:09:46 -07:00
Dustin LuongandCopybara-Service 57f3cc3094 Add QwQ deployment notebook 
PiperOrigin-RevId: 738183275
 2025-03-18 16:29:26 -07:00
Dustin LuongandCopybara-Service abdd887fa1 Set model_garden_source_model_name for model_garden_phi4_deployment notebook. 
PiperOrigin-RevId: 722840147
 2025-02-03 16:25:21 -08:00
Dustin LuongandCopybara-Service 711a4f0b8c Set model_garden_source_model_name for deployment notebooks. 
PiperOrigin-RevId: 722701496
 2025-02-03 10:06:48 -08:00
Dustin LuongandCopybara-Service 3c06e4797a Set model_garden_source_model_name for some model garden deployment notebooks. 
PiperOrigin-RevId: 721846318
 2025-01-31 11:39:27 -08:00
Dustin LuongandCopybara-Service 6fabc23db6 Set model_garden_source_model_name for vllm deployments. 
PiperOrigin-RevId: 720345103
 2025-01-27 16:20:59 -08:00
Dustin LuongandCopybara-Service 18305e35ea Set model_garden_source_model_name for hexllm deployments. 
PiperOrigin-RevId: 720341876
 2025-01-27 16:09:59 -08:00
Dustin LuongandCopybara-Service b71f0ec2dc Set model_garden_source_model_name for optimized vllm deployments. 
PiperOrigin-RevId: 720317678
 2025-01-27 14:54:29 -08:00
Dustin LuongandCopybara-Service d7fe713f7f Set model_garden_source_model_name for TGI deployments. 
PiperOrigin-RevId: 720312091
 2025-01-27 14:40:10 -08:00
Dustin LuongandCopybara-Service 52925286ec Set model_garden_source_model_name for pytorch inference deployments. 
PiperOrigin-RevId: 720311822
 2025-01-27 14:38:52 -08:00
Dustin LuongandCopybara-Service b7b14ba7d8 Set model_garden_source_model_name for llama3 
reference implementation deployment.

PiperOrigin-RevId: 720311748
 2025-01-27 14:38:41 -08:00
Dustin LuongandCopybara-Service 5e3c07f72e Set model_garden_source_model_name for TEI deployments. 
PiperOrigin-RevId: 720311569
 2025-01-27 14:37:21 -08:00
Dustin LuongandCopybara-Service 25b3364236 No public description 
PiperOrigin-RevId: 713694601
 2025-01-09 09:13:27 -08:00
Dustin LuongandCopybara-Service 883e1e5fc1 Set system_labels in notebooks 
PiperOrigin-RevId: 713040032
 2025-01-07 14:20:25 -08:00
Dustin LuongandCopybara-Service a1d4026020 Update the notebook to use the Vertex SDK to send requests to the deployed endpoint instead of openai SDK. 
PiperOrigin-RevId: 685713862
 2024-10-14 08:23:23 -07:00
Dustin LuongandCopybara-Service bd3283b2a6 Internal change. 
PiperOrigin-RevId: 681516025
 2024-10-02 17:49:03 -07:00
Dustin LuongandCopybara-Service fc917137da Use vLLM docker to deploy dolly-v2 model. 
PiperOrigin-RevId: 673051532
 2024-09-10 12:00:12 -07:00
Dustin LuongandCopybara-Service d6a8ed040a Update deploy function. 
PiperOrigin-RevId: 672608260
 2024-09-09 11:17:52 -07:00
Dustin LuongandCopybara-Service 8e7d030426 No public description 
PiperOrigin-RevId: 663483238
 2024-08-16 18:31:07 -07:00