-
Notifications
You must be signed in to change notification settings - Fork 4
Comparing changes
Open a pull request
base repository: CogStack/CogStack-ModelServe
base: embeddings
head repository: CogStack/CogStack-ModelServe
compare: main
- 13 commits
- 86 files changed
- 2 contributors
Commits on Jan 14, 2026
-
Configuration menu - View commit details
-
Copy full SHA for 12bc6ff - Browse repository at this point
Copy the full SHA 12bc6ffView commit details
Commits on Jan 20, 2026
-
Merge pull request #36 from CogStack/mongodb
Bump mongodb to tackle CVE-2025-14847
Configuration menu - View commit details
-
Copy full SHA for 5c83f01 - Browse repository at this point
Copy the full SHA 5c83f01View commit details -
Merge pull request #37 from CogStack/embeddings
Add embedding creation for MedCAT and HF NER models
Configuration menu - View commit details
-
Copy full SHA for 042dd83 - Browse repository at this point
Copy the full SHA 042dd83View commit details
Commits on Feb 9, 2026
-
Add MCP server to integrate CMS capabilities for LLM responses (#38)
* feat: add MCP server to integrate CMS capabilities for LLM responses
Configuration menu - View commit details
-
Copy full SHA for ed620d7 - Browse repository at this point
Copy the full SHA ed620d7View commit details
Commits on Feb 11, 2026
-
feat: add the endpoint for legacy v1 completion
feat: auto-utilise the local chat template if detected feat: add the option to generate full sentences feat: add the option for local 8bit quantisation feat: add the gpt oss chat template fix: skip quantisation if the model being loaded is already quantised
Configuration menu - View commit details
-
Copy full SHA for b0c845e - Browse repository at this point
Copy the full SHA b0c845eView commit details
Commits on Feb 13, 2026
-
Merge pull request #39 from CogStack/llm-serving
Add the endpoint for legacy v1 completion and the local 8bit quantisation
Configuration menu - View commit details
-
Copy full SHA for de5e049 - Browse repository at this point
Copy the full SHA de5e049View commit details -
Configuration menu - View commit details
-
Copy full SHA for 876b8fb - Browse repository at this point
Copy the full SHA 876b8fbView commit details -
Merge pull request #40 from CogStack/doc-n-reorg
Improve READMEs and refactor the OAuth flow
Configuration menu - View commit details
-
Copy full SHA for 18c4efa - Browse repository at this point
Copy the full SHA 18c4efaView commit details
Commits on Mar 6, 2026
-
feat: add the enpoint for v1 models and list models
feat: add micro batching and lower CPU usage during model loading feat: ensure the pad token for generative models feat: use the async streamer during async generation feat: apply timeout to text generation fix: fix the property name for stop sequences in OpenAI requests
Configuration menu - View commit details
-
Copy full SHA for 874c1fa - Browse repository at this point
Copy the full SHA 874c1faView commit details
Commits on Mar 9, 2026
-
Configuration menu - View commit details
-
Copy full SHA for 3823b76 - Browse repository at this point
Copy the full SHA 3823b76View commit details
Commits on Mar 10, 2026
-
Configuration menu - View commit details
-
Copy full SHA for 184832d - Browse repository at this point
Copy the full SHA 184832dView commit details
Commits on Mar 13, 2026
-
Merge pull request #41 from CogStack/llm-gen2
Add micro batching and enpoints for v1 list_models and get_model
Configuration menu - View commit details
-
Copy full SHA for 98554f8 - Browse repository at this point
Copy the full SHA 98554f8View commit details -
Configuration menu - View commit details
-
Copy full SHA for 86e4e68 - Browse repository at this point
Copy the full SHA 86e4e68View commit details
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff embeddings...main