summaryrefslogtreecommitdiffstats
path: root/model-integration/src/test
Commit message (Expand)AuthorAgeFilesLines
* Disable local LLM unit testsLester Solbakken2024-04-161-1/+6
* Reapply "Lesters/add local llms 2"Lester Solbakken2024-04-165-0/+470
* Revert "Lesters/add local llms 2"Harald Musum2024-04-155-470/+0
* Reapply "Lesters/add local llms"Lester Solbakken2024-04-155-0/+470
* Revert "Lesters/add local llms"Lester Solbakken2024-04-155-470/+0
* Merge branch 'master' into lesters/add-local-llmsLester Solbakken2024-04-121-3/+2
|\
* | Move LLM client stuff from container-search to model-integrationLester Solbakken2024-04-125-0/+471
|/
* cache more and re-factorJo Kristian Bergum2024-04-081-13/+45
* Key by embedder id and don't recompute inputsJon Bratseth2024-04-071-25/+40
* Add caching of onnx inference output using Context cacheJo Kristian Bergum2024-04-041-4/+20
* Support for dimensionality flexbility and caching onnx inference output using...Jo Kristian Bergum2024-04-041-27/+97
* Add some more tests on the binarizationJo Kristian Bergum2024-03-301-1/+38
* relax testing on float strings due to small inference differences in platformsJo Kristian Bergum2024-03-291-5/+10
* Add support for binarization and matryoshka for hf-embedderJo Kristian Bergum2024-03-292-0/+84
* Support embedding into rank 3 tensorsJon Bratseth2024-02-021-9/+16
* - Add alternative sparsify implementation using generic tensor.reduce/map.Henning Baldersheim2024-01-311-6/+8
* - Put the inner loops in separate methods. This improves ability to inline.Henning Baldersheim2024-01-201-1/+1
* Add a class for assist efficient traversal of dimensions in an IndexedTensor.Henning Baldersheim2024-01-191-2/+2
* Avoid generic reduce and keep PAD token embeddingJo Kristian Bergum2024-01-151-13/+31
* remove extra spaceJo Kristian Bergum2024-01-111-1/+1
* address reviewJo Kristian Bergum2024-01-111-1/+2
* Avoid generic reduce to reduce gc pressureJo Kristian Bergum2024-01-111-1/+14
* handle multilingual models betterJo Kristian Bergum2024-01-062-5/+85
* Allow mapped 1d tensor for embed expressionsJo Kristian Bergum2023-12-171-3/+1
* Add a splade embedder implementationJo Kristian Bergum2023-12-154-0/+30794
* add simple expandBitTensor functionArne Juul2023-11-101-3/+18
* Add support and upgrade opsetJo Kristian Bergum2023-10-263-6/+8
* Add support for bfloat16 and float16Jo Kristian Bergum2023-10-264-0/+82
* Less verbose logging when failing to find CUDA and it is optionalJo Kristian Bergum2023-10-261-0/+51
* Update copyrightJon Bratseth2023-10-0934-32/+36
* Don't index PAD and re-factoringJo Kristian Bergum2023-09-261-9/+9
* Add config options + licenseJo Kristian Bergum2023-09-211-0/+1
* Add ColBERT embedderJo Kristian Bergum2023-09-213-0/+300
* Add generic metrics for embeddersBjørn Christian Seime2023-08-041-1/+2
* update onnx.protoArne Juul2023-06-231-2/+2
* Remove dead codeBjørn Christian Seime2023-05-261-36/+0
* Put the openai client in a separate componentJon Bratseth2023-04-252-38/+3
* Avoid ignored directory nameJon Bratseth2023-04-191-2/+1
* Llm completion abstraction and OpenAi implementationJon Bratseth2023-04-191-0/+38
* Support loading ONNX models through byte arrayBjørn Christian Seime2023-03-302-21/+88
* Don't reuse runtime between methodsBjørn Christian Seime2023-03-301-21/+18
* Replace `OnnxEvaluatorCache` with OnnxRuntimeBjørn Christian Seime2023-02-276-74/+85
* Cache Onnx model instancesBjørn Christian Seime2023-02-221-0/+38
* Add initial text generator componentLester Solbakken2023-02-186-2/+118
* ensure outputs with names as promised by getOutputInfo()Arne Juul2023-02-102-0/+102
* DJL-based HuggingFaceEmbedder prototypeAndrii Yurkiv2023-01-041-0/+50
* Revert "Revert "- Reduce usage of guava.""Henning Baldersheim2022-12-011-4/+8
* Revert "- Reduce usage of guava."Henning Baldersheim2022-12-011-8/+4
* - Reduce usage of guava.Henning Baldersheim2022-12-011-4/+8
* Revert "Revert "Revert "Revert "Balder/model importing code in config model [...Henning Baldersheim2022-11-093-13/+12