summaryrefslogtreecommitdiffstats
path: root/model-integration/src/main/java
Commit message (Expand)AuthorAgeFilesLines
...
* Make HF tokenizer a separate embedderBjørn Christian Seime2023-05-114-177/+6
* Don't specify both package and namespaceBjørn Christian Seime2023-05-111-0/+1
* Reapply "Bjorncs/embedder onnx gpu"Bjørn Christian Seime2023-05-094-6/+40
* Revert "Bjorncs/embedder onnx gpu"Geir Storli2023-05-084-40/+6
* Handle nullsBjørn Christian Seime2023-05-081-0/+4
* fixup! Require GPU when requested and available for Bert + HF embeddersBjørn Christian Seime2023-05-081-1/+1
* Require GPU when requested and available for Bert + HF embeddersBjørn Christian Seime2023-05-083-1/+4
* Require GPU when available for ONNX evaluation in global-phase and embeddersBjørn Christian Seime2023-05-082-5/+36
* Make thread pool size configurableBjørn Christian Seime2023-05-054-17/+19
* Make normalization optionalBjørn Christian Seime2023-05-051-1/+4
* Allow for manual configuration of GPUBjørn Christian Seime2023-05-051-1/+5
* Move config to same package as componentBjørn Christian Seime2023-05-051-1/+0
* Split out HF TokenizerBjørn Christian Seime2023-05-054-23/+174
* Put the openai client in a separate componentJon Bratseth2023-04-2511-279/+4
* Export APIJon Bratseth2023-04-203-0/+33
* Merge pull request #26777 from vespa-engine/bratseth/openai-clientJon Bratseth2023-04-198-0/+258
|\
| * Use record and use default record toStringJon Bratseth2023-04-191-9/+1
| * Fix typoJon Bratseth2023-04-191-1/+1
| * Avoid ignored directory nameJon Bratseth2023-04-191-0/+44
| * Llm completion abstraction and OpenAi implementationJon Bratseth2023-04-197-0/+222
* | Merge pull request #26753 from vespa-engine/bjorncs/global-phaseArne H Juul2023-04-191-5/+9
|\ \ | |/ |/|
| * Use quarter vcpu by default if execution mode is parallelBjørn Christian Seime2023-04-171-5/+9
* | Merge pull request #26754 from vespa-engine/bratseth/jdk20Jon Bratseth2023-04-181-2/+2
|\ \
| * | Build with jdk20Jon Bratseth2023-04-171-2/+2
* | | Pull endtokenJon Bratseth2023-04-181-1/+1
* | | Revert "Merge pull request #26744 from vespa-engine/revert-26708-allow-start-...Jon Bratseth2023-04-181-8/+10
| |/ |/|
* | Revert "Allow start end sequence tokens as args bertbaseembedder"Jon Bratseth2023-04-141-10/+8
|/
* Include createTokenTypeIdsconnell gough2023-04-131-0/+1
* Remove separator input and fix spelling errorconnell gough2023-04-131-3/+2
* Add special tokens as arguments and allow tokenTypeIds to be nullconnell gough2023-04-131-7/+9
* Support loading ONNX models through byte arrayBjørn Christian Seime2023-03-302-15/+74
* Revert "Arnej/unify cell type conversion"Henning Baldersheim2023-03-122-39/+20
* cell-type conversions should matchArne Juul2023-03-102-20/+39
* Extend AbstractComponent not AbstractResourceBjørn Christian Seime2023-02-283-9/+9
* Replace `OnnxEvaluatorCache` with OnnxRuntimeBjørn Christian Seime2023-02-277-154/+234
* handle non-identifier onnx input/output names: instead of the conflictingArne Juul2023-02-221-0/+30
* Cache Onnx model instancesBjørn Christian Seime2023-02-221-0/+88
* Make OnnxEvaluator closableBjørn Christian Seime2023-02-221-1/+12
* Implement equals()/hashCode()Bjørn Christian Seime2023-02-221-1/+17
* Add initial text generator componentLester Solbakken2023-02-182-0/+260
* ensure outputs with names as promised by getOutputInfo()Arne Juul2023-02-101-1/+21
* Fix GPU detectionMartin Polden2023-02-091-1/+1
* Allow fallback to CPU if nodes are provisioned without GPUMartin Polden2023-02-082-13/+24
* Remove 'required' attributeMartin Polden2023-01-262-22/+14
* Skip CUDA entirely if GPU device is optionalMartin Polden2023-01-262-24/+39
* Do not filter on error codeMartin Polden2023-01-241-4/+1
* Support configuration of GPU device to use in ONNX modelMartin Polden2023-01-231-1/+24
* Unify on Streams.toList()Henning Baldersheim2023-01-172-4/+3
* DJL-based HuggingFaceEmbedder prototypeAndrii Yurkiv2023-01-041-0/+158
* trying to make an OnnxEvaluator with empty path would failArne Juul2022-12-121-0/+8