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/add-folding-flag
arnej/cosmetic-message-fix
arnej/golang-slime-port-1
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/prepare-for-string_view-3
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/theodorkl/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/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
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
about
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
model-integration
/
src
/
main
/
java
/
ai
Commit message (
Expand
)
Author
Age
Files
Lines
*
Avoid methods deprecated in jackson 2.17.1
Henning Baldersheim
2024-05-06
1
-2
/
+2
*
Revert "Update jackson2.vespa.version to v2.17.0"
Henning Baldersheim
2024-05-06
1
-2
/
+2
*
Merge pull request #31120 from vespa-engine/lesters/local-llm-timeout
Harald Musum
2024-05-06
1
-5
/
+33
|
\
|
*
Add timeout for requests waiting to start local llm inference
Lester Solbakken
2024-05-06
1
-5
/
+33
*
|
Avoid deprecated methods.
Henning Baldersheim
2024-05-06
1
-2
/
+2
|
/
*
add prepend support
Jo Kristian Bergum
2024-04-25
1
-1
/
+17
*
Remove unneccessary import
Lester Solbakken
2024-04-22
1
-1
/
+0
*
Set minimum number of threads to 1
Lester Solbakken
2024-04-22
1
-1
/
+1
*
Reapply "Lesters/add local llms 2"
Lester Solbakken
2024-04-16
4
-0
/
+256
*
Revert "Lesters/add local llms 2"
Harald Musum
2024-04-15
4
-256
/
+0
*
Reapply "Lesters/add local llms"
Lester Solbakken
2024-04-15
4
-0
/
+256
*
Revert "Lesters/add local llms"
Lester Solbakken
2024-04-15
4
-256
/
+0
*
Merge branch 'master' into lesters/add-local-llms
Lester Solbakken
2024-04-12
8
-20
/
+13
|
\
|
*
Unify on List.of
Henning Baldersheim
2024-04-11
7
-17
/
+11
|
*
Unify on Map.of
Henning Baldersheim
2024-04-11
1
-3
/
+2
*
|
Move LLM client stuff from container-search to model-integration
Lester Solbakken
2024-04-12
4
-0
/
+256
|
/
*
cache more and re-factor
Jo Kristian Bergum
2024-04-08
1
-55
/
+64
*
Key by embedder id and don't recompute inputs
Jon Bratseth
2024-04-07
1
-40
/
+33
*
Add equivalent to `Map.computeIfAbsent()` to simplify typical usage of the cache
Bjørn Christian Seime
2024-04-04
2
-20
/
+3
*
Add caching of onnx inference output using Context cache
Jo Kristian Bergum
2024-04-04
1
-14
/
+35
*
Support for dimensionality flexbility and caching onnx inference output using...
Jo Kristian Bergum
2024-04-04
1
-26
/
+34
*
Add some more tests on the binarization
Jo Kristian Bergum
2024-03-30
1
-1
/
+1
*
fix unwanted import
Jo Kristian Bergum
2024-03-29
1
-1
/
+0
*
Add support for binarization and matryoshka for hf-embedder
Jo Kristian Bergum
2024-03-29
1
-5
/
+56
*
All embedders are the same
Jon Bratseth
2024-02-09
1
-2
/
+2
*
Support embedding into rank 3 tensors
Jon Bratseth
2024-02-02
2
-20
/
+26
*
- Add alternative sparsify implementation using generic tensor.reduce/map.
Henning Baldersheim
2024-01-31
1
-3
/
+44
*
- Put the inner loops in separate methods. This improves ability to inline.
Henning Baldersheim
2024-01-20
1
-53
/
+51
*
Rename getIndex => getDirectIndex
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
/
+7
*
Cache sizes.totalSize() in variable to prevent recomputation.
Henning Baldersheim
2024-01-18
1
-20
/
+19
*
Since both value and log(value) are monotonically increasing for value >= 1,
Henning Baldersheim
2024-01-18
1
-8
/
+8
*
Construct array right away instead of going via a single element list and the...
Henning Baldersheim
2024-01-18
1
-5
/
+15
*
Avoid generic reduce and keep PAD token embedding
Jo Kristian Bergum
2024-01-15
1
-11
/
+16
*
address review
Jo Kristian Bergum
2024-01-11
1
-42
/
+23
*
Avoid generic reduce to reduce gc pressure
Jo Kristian Bergum
2024-01-11
1
-18
/
+47
*
final
Jo Kristian Bergum
2024-01-06
1
-1
/
+1
*
handle multilingual models better
Jo Kristian Bergum
2024-01-06
1
-60
/
+62
*
Allow mapped 1d tensor for embed expressions
Jo Kristian Bergum
2023-12-17
1
-10
/
+12
*
Add a splade embedder implementation
Jo Kristian Bergum
2023-12-15
1
-0
/
+168
*
Move Jackson util from vespajlib to container-core.
Henning Baldersheim
2023-11-24
3
-3
/
+3
*
jackson 2.16 changes some of its default settings so we consolidate our use o...
Henning Baldersheim
2023-11-23
3
-8
/
+7
*
unpack_bits_from_int8 -> unpack_bits
Arne Juul
2023-11-10
1
-2
/
+2
*
add simple expandBitTensor function
Arne Juul
2023-11-10
1
-6
/
+17
*
Add support and upgrade opset
Jo Kristian Bergum
2023-10-26
1
-1
/
+23
*
Less verbose logging when failing to find CUDA and it is optional
Jo Kristian Bergum
2023-10-26
1
-2
/
+2
*
Disable CPU arena allocator for ONNX
Bjørn Christian Seime
2023-10-19
1
-0
/
+1
*
Update copyright
Jon Bratseth
2023-10-09
83
-86
/
+90
*
Don't index PAD and re-factoring
Jo Kristian Bergum
2023-09-26
1
-32
/
+28
*
Add config options + license
Jo Kristian Bergum
2023-09-21
1
-0
/
+1
[next]