index
:
vespa
6
7
andreer/permanent-enclave-flag
aressem/test-dummy
aressem/test-pr-bk
aressem/test-pr-build-3
aressem/test-valgrind
arnej/add-feature-flag
arnej/configurable-legacy-query-parsing
arnej/cosmetic-message-fix
arnej/golang-slime-port-1
arnej/handle-ideographic-comma
arnej/remove-convert-in-calculator
arnej/use-our-shell-quote
arnej/wip-sand-fixups
balder/apply-termwise-filters-on-match-phase-2
balder/cpu-specific-compiles-for-bit-operations
balder/deinline
balder/hosted-always-convert-percentages-in-config-model
balder/no-longer-need-commit-and-wait
balder/prepare-for-hw-specialized-hamming-distance
balder/prepare-for-string_view-1
balder/thread-local-jetty-bytebuffer-pool
balder/update-defaults-for-use-xxx-fetch-postings
balder/zncurve
bjormel/aws-main-controller
bjormel/aws-main-controller-take2
bratseth/grouping-trace
bratseth/linguistics-context-rebased
bratseth/more-exclusive-take-2
bratseth/stem-prefixes
bratseth/streamed-fill
hakonhall/enumerate-all-prod-regions
hakonhall/fix-remembertoupdatesystemflagsdataarchive-javadoc
havardpe/enable-nested-ctf-meta-data
havardpe/extract-default-query-feature-values
havardpe/protoc-gen-csi
interns/languageserver
interns/magnus/expandGrammar
jdk21-preparations
jonmv/allow-private-endpoints-in-dev-perf
jonmv/dependency-inversion-for-mbus-config
jvenstad/utils
kkraune/ci-warning
ldalves/querybuilder
leandroalves/prod-controller
lesters/bert-testing
lesters/external-llms
lesters/stateless-onnx-eval-once
master
mortent/calypso
mortent/new-public-cd-endpoint
mpolden/feature-flag-status
mpolden/update-abi
olaa/delete-flags
olaa/otel-config-model
renovate/junit5-monorepo
renovate/major-protobuf.vespa.version
renovate/maven-shade-plugin.vespa.version
revert-26576-revert-26567-bjorncs/cloud-app-validation
revert-26584-revert-26578-bjorncs/tlsv13
revert-27857-bjorncs/tls13
revert-28660-revert-28656-hmusum/fix-onnx-model-cost
revert-30559-toregge/require-vespa-build-dependencies-for-vespa-devel
revert-31808-aressem/skip-verification
vekterli/change-test-and-set-update-not-found-semantics
yngveaasheim/skeleton-for-component-in-metrics-enum
An engine for low-latency computation over large data sets
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
model-integration
/
src
/
test
Commit message (
Expand
)
Author
Age
Files
Lines
*
Disable local LLM unit tests
Lester Solbakken
2024-04-16
1
-1
/
+6
*
Reapply "Lesters/add local llms 2"
Lester Solbakken
2024-04-16
5
-0
/
+470
*
Revert "Lesters/add local llms 2"
Harald Musum
2024-04-15
5
-470
/
+0
*
Reapply "Lesters/add local llms"
Lester Solbakken
2024-04-15
5
-0
/
+470
*
Revert "Lesters/add local llms"
Lester Solbakken
2024-04-15
5
-470
/
+0
*
Merge branch 'master' into lesters/add-local-llms
Lester Solbakken
2024-04-12
1
-3
/
+2
|
\
*
|
Move LLM client stuff from container-search to model-integration
Lester Solbakken
2024-04-12
5
-0
/
+471
|
/
*
cache more and re-factor
Jo Kristian Bergum
2024-04-08
1
-13
/
+45
*
Key by embedder id and don't recompute inputs
Jon Bratseth
2024-04-07
1
-25
/
+40
*
Add caching of onnx inference output using Context cache
Jo Kristian Bergum
2024-04-04
1
-4
/
+20
*
Support for dimensionality flexbility and caching onnx inference output using...
Jo Kristian Bergum
2024-04-04
1
-27
/
+97
*
Add some more tests on the binarization
Jo Kristian Bergum
2024-03-30
1
-1
/
+38
*
relax testing on float strings due to small inference differences in platforms
Jo Kristian Bergum
2024-03-29
1
-5
/
+10
*
Add support for binarization and matryoshka for hf-embedder
Jo Kristian Bergum
2024-03-29
2
-0
/
+84
*
Support embedding into rank 3 tensors
Jon Bratseth
2024-02-02
1
-9
/
+16
*
- Add alternative sparsify implementation using generic tensor.reduce/map.
Henning Baldersheim
2024-01-31
1
-6
/
+8
*
- Put the inner loops in separate methods. This improves ability to inline.
Henning Baldersheim
2024-01-20
1
-1
/
+1
*
Add a class for assist efficient traversal of dimensions in an IndexedTensor.
Henning Baldersheim
2024-01-19
1
-2
/
+2
*
Avoid generic reduce and keep PAD token embedding
Jo Kristian Bergum
2024-01-15
1
-13
/
+31
*
remove extra space
Jo Kristian Bergum
2024-01-11
1
-1
/
+1
*
address review
Jo Kristian Bergum
2024-01-11
1
-1
/
+2
*
Avoid generic reduce to reduce gc pressure
Jo Kristian Bergum
2024-01-11
1
-1
/
+14
*
handle multilingual models better
Jo Kristian Bergum
2024-01-06
2
-5
/
+85
*
Allow mapped 1d tensor for embed expressions
Jo Kristian Bergum
2023-12-17
1
-3
/
+1
*
Add a splade embedder implementation
Jo Kristian Bergum
2023-12-15
4
-0
/
+30794
*
add simple expandBitTensor function
Arne Juul
2023-11-10
1
-3
/
+18
*
Add support and upgrade opset
Jo Kristian Bergum
2023-10-26
3
-6
/
+8
*
Add support for bfloat16 and float16
Jo Kristian Bergum
2023-10-26
4
-0
/
+82
*
Less verbose logging when failing to find CUDA and it is optional
Jo Kristian Bergum
2023-10-26
1
-0
/
+51
*
Update copyright
Jon Bratseth
2023-10-09
34
-32
/
+36
*
Don't index PAD and re-factoring
Jo Kristian Bergum
2023-09-26
1
-9
/
+9
*
Add config options + license
Jo Kristian Bergum
2023-09-21
1
-0
/
+1
*
Add ColBERT embedder
Jo Kristian Bergum
2023-09-21
3
-0
/
+300
*
Add generic metrics for embedders
Bjørn Christian Seime
2023-08-04
1
-1
/
+2
*
update onnx.proto
Arne Juul
2023-06-23
1
-2
/
+2
*
Remove dead code
Bjørn Christian Seime
2023-05-26
1
-36
/
+0
*
Put the openai client in a separate component
Jon Bratseth
2023-04-25
2
-38
/
+3
*
Avoid ignored directory name
Jon Bratseth
2023-04-19
1
-2
/
+1
*
Llm completion abstraction and OpenAi implementation
Jon Bratseth
2023-04-19
1
-0
/
+38
*
Support loading ONNX models through byte array
Bjørn Christian Seime
2023-03-30
2
-21
/
+88
*
Don't reuse runtime between methods
Bjørn Christian Seime
2023-03-30
1
-21
/
+18
*
Replace `OnnxEvaluatorCache` with OnnxRuntime
Bjørn Christian Seime
2023-02-27
6
-74
/
+85
*
Cache Onnx model instances
Bjørn Christian Seime
2023-02-22
1
-0
/
+38
*
Add initial text generator component
Lester Solbakken
2023-02-18
6
-2
/
+118
*
ensure outputs with names as promised by getOutputInfo()
Arne Juul
2023-02-10
2
-0
/
+102
*
DJL-based HuggingFaceEmbedder prototype
Andrii Yurkiv
2023-01-04
1
-0
/
+50
*
Revert "Revert "- Reduce usage of guava.""
Henning Baldersheim
2022-12-01
1
-4
/
+8
*
Revert "- Reduce usage of guava."
Henning Baldersheim
2022-12-01
1
-8
/
+4
*
- Reduce usage of guava.
Henning Baldersheim
2022-12-01
1
-4
/
+8
*
Revert "Revert "Revert "Revert "Balder/model importing code in config model [...
Henning Baldersheim
2022-11-09
3
-13
/
+12
[next]