summaryrefslogtreecommitdiffstats
path: root/model-integration/src/main/java
Commit message (Expand)AuthorAgeFilesLines
* All embedders are the sameJon Bratseth2024-02-091-2/+2
* Support embedding into rank 3 tensorsJon Bratseth2024-02-022-20/+26
* - Add alternative sparsify implementation using generic tensor.reduce/map.Henning Baldersheim2024-01-311-3/+44
* - Put the inner loops in separate methods. This improves ability to inline.Henning Baldersheim2024-01-201-53/+51
* Rename getIndex => getDirectIndexHenning Baldersheim2024-01-201-1/+1
* Add a class for assist efficient traversal of dimensions in an IndexedTensor.Henning Baldersheim2024-01-191-2/+7
* Cache sizes.totalSize() in variable to prevent recomputation.Henning Baldersheim2024-01-181-20/+19
* Since both value and log(value) are monotonically increasing for value >= 1,Henning Baldersheim2024-01-181-8/+8
* Construct array right away instead of going via a single element list and the...Henning Baldersheim2024-01-181-5/+15
* Avoid generic reduce and keep PAD token embeddingJo Kristian Bergum2024-01-151-11/+16
* address reviewJo Kristian Bergum2024-01-111-42/+23
* Avoid generic reduce to reduce gc pressureJo Kristian Bergum2024-01-111-18/+47
* finalJo Kristian Bergum2024-01-061-1/+1
* handle multilingual models betterJo Kristian Bergum2024-01-061-60/+62
* Allow mapped 1d tensor for embed expressionsJo Kristian Bergum2023-12-171-10/+12
* Add a splade embedder implementationJo Kristian Bergum2023-12-151-0/+168
* Move Jackson util from vespajlib to container-core.Henning Baldersheim2023-11-243-3/+3
* jackson 2.16 changes some of its default settings so we consolidate our use o...Henning Baldersheim2023-11-233-8/+7
* unpack_bits_from_int8 -> unpack_bitsArne Juul2023-11-101-2/+2
* add simple expandBitTensor functionArne Juul2023-11-101-6/+17
* Add support and upgrade opsetJo Kristian Bergum2023-10-261-1/+23
* Less verbose logging when failing to find CUDA and it is optionalJo Kristian Bergum2023-10-261-2/+2
* Disable CPU arena allocator for ONNXBjørn Christian Seime2023-10-191-0/+1
* Update copyrightJon Bratseth2023-10-0983-86/+90
* Don't index PAD and re-factoringJo Kristian Bergum2023-09-261-32/+28
* Add config options + licenseJo Kristian Bergum2023-09-211-0/+1
* Ensure Onnx/Hugginface resources are cleaned up on deconstructionBjørn Christian Seime2023-09-211-0/+6
* Add ColBERT embedderJo Kristian Bergum2023-09-211-0/+299
* - Use equals when comparing Optional<Long>Henning Baldersheim2023-09-132-4/+4
* Use thread safe hash mapBjørn Christian Seime2023-08-311-2/+2
* Merge pull request #27969 from vespa-engine/bjorncs/embedder-metricsJon Bratseth2023-08-313-7/+80
|\
| * Allow sampling of fractional millisBjørn Christian Seime2023-08-253-15/+10
| * Add generic metrics for embeddersBjørn Christian Seime2023-08-043-7/+85
* | Better error message when importing models with illegal namesLester Solbakken2023-08-291-0/+25
|/
* Log when GPU configuration is successfulMartin Polden2023-07-191-3/+8
* Log warning when failing to use GPUMartin Polden2023-07-191-1/+6
* update onnx.protoArne Juul2023-06-232-5/+7
* Prefer truncation configuration from tokenizer modelBjørn Christian Seime2023-06-121-6/+19
* Add missing wiring of pooling strategyBjørn Christian Seime2023-06-081-11/+1
* Disable padding and make it configurableBjørn Christian Seime2023-06-081-0/+1
* Make pooling strategy configurable for Huggingface embedderBjørn Christian Seime2023-06-053-17/+54
* Properly ignore token type ids from tokenizer if disabledBjørn Christian Seime2023-05-301-2/+2
* Remove dead codeBjørn Christian Seime2023-05-261-7/+0
* Make truncation and max length configurableBjørn Christian Seime2023-05-261-12/+3
* Revert "Revert "Bjorncs/huggingface tokenizer""Bjørn Christian Seime2023-05-124-190/+28
* Revert "Bjorncs/huggingface tokenizer"Arnstein Ressem2023-05-124-28/+190
* Handle models requiring token type idsBjørn Christian Seime2023-05-111-13/+19
* Don't lower caseBjørn Christian Seime2023-05-111-1/+1
* Disable special tokens by defaultBjørn Christian Seime2023-05-111-0/+1
* Mark HF integration as betaBjørn Christian Seime2023-05-111-0/+2