summaryrefslogtreecommitdiffstats
path: root/config-model
Commit message (Collapse)AuthorAgeFilesLines
* Remove "vds.filestor.*" metrics from consumer fleetcontroller ↵Geir Storli2018-03-202-22/+4
| | | | (clustercontroller) that are not used.
* Merge pull request #5378 from vespa-engine/balder/no-more-thread-prioritiesTor Brede Vekterli2018-03-203-73/+17
|\ | | | | Balder/no more thread priorities
| * No need for an array when you just need a countHenning Baldersheim2018-03-193-73/+17
| |
* | Merge pull request #5377 from vespa-engine/bratseth/reduce-old-junit-usageJon Bratseth2018-03-196-12/+10
|\ \ | |/ |/| Nonfunctional changes only
| * Nonfunctional changes onlyJon Bratseth2018-03-196-12/+10
| |
* | Add coverage metrics to default vespa metric setHenning Baldersheim2018-03-161-0/+4
| |
* | Prepare for removing some unused or noop methods from filedistribution APIHarald Musum2018-03-153-12/+20
|/
* Merge pull request #5285 from vespa-engine/arnej/add-gzip-accesslogsJon Bratseth2018-03-152-3/+18
|\ | | | | hack in gzip of access logs
| * ensure gzip of access logs for hosted vespa onlyArne Juul2018-03-122-3/+18
| |
* | Prefix macro names by modelName to avoid name conflictsJon Bratseth2018-03-131-10/+10
| |
* | Merge pull request #5309 from vespa-engine/bratseth/disambiguate-constantsJon Bratseth2018-03-133-45/+49
|\ \ | | | | | | Prefix constants by model name
| * | Prefix constants by model nameJon Bratseth2018-03-133-45/+49
| | | | | | | | | | | | | | | | | | | | | | | | | | | Large constants are cross rank profiles. This avoids name conflicts when multiple models are used. It is not strictly necessary because the user can always disambiguate when chosing names, but there is a scenario where conflicts are plausible and leaving this to users is inconvenient: Multiple versions of the "same" model are tested in different rank profiles.
* | | Tensor fields are out of betaJon Bratseth2018-03-121-8/+0
|/ /
* / Use tensorflow 1.6Henning Baldersheim2018-03-121-2/+2
|/
* filedistributorservice does not exist anymoreHarald Musum2018-03-101-16/+12
|
* Merge pull request #5267 from vespa-engine/lesters/tensorflow-broadcastingJon Bratseth2018-03-091-4/+4
|\ | | | | Make TensorFlow import joins compatible with broadcasting
| * Make TensorFlow import joins compatible with broadcastingLester Solbakken2018-03-081-4/+4
| |
* | Merge pull request #5264 from vespa-engine/gjoranv/secret-storegjoranv2018-03-097-10/+94
|\ \ | | | | | | Gjoranv/secret store
| * | Allow setting up a secret store from services.xml.gjoranv2018-03-086-5/+88
| | | | | | | | | | | | - The actual implementation must be added by a model amender.
| * | Extract method to keep addClusterContent clean and "short".gjoranv2018-03-081-2/+4
| | |
| * | Add myself as author.gjoranv2018-03-081-0/+1
| | |
| * | Improve comment.gjoranv2018-03-081-1/+1
| | |
| * | Remove invalid TODO. DomQrserverClusterBuilder n'existe plus.gjoranv2018-03-081-2/+0
| | |
* | | Merge pull request #5265 from ↵Geir Storli2018-03-081-0/+8
|\ \ \ | | | | | | | | | | | | | | | | vespa-engine/toregge/expose-threading-service-metrics Expose threading service metrics.
| * | | Expose threading service metrics.Tor Egge2018-03-081-0/+8
| |/ /
* | | Merge pull request #5266 from ↵Jon Bratseth2018-03-081-2/+1
|\ \ \ | |_|/ |/| | | | | | | | vespa-engine/bratseth/convert-tf-tensor-on-command-line Bratseth/convert tf tensor on command line
| * | Log OrderedTensorType of imported TensorFlow variablesJon Bratseth2018-03-081-2/+1
| |/
* / Add batch dimension reduction in generated macrosLester Solbakken2018-03-082-64/+113
|/ | | | | | Check for inputs/placeholders containing batch dimensions inside generated macros, and insert reduce operations. Expand those dimensions back at the top level expression.
* Merge pull request #5241 from vespa-engine/bratseth/tf-constants-in-parent-docLester Solbakken2018-03-072-21/+129
|\ | | | | Bratseth/tf constants in parent doc
| * Allow macros to replace TenorFlow variablesJon Bratseth2018-03-072-21/+129
| | | | | | | | | | | | Also, remove quoting of constant arguments generated in TensorFlow as that is unnecessary now and is interpreted as a string constant argument to a macro.
* | Fix unit test after correct dimension renamingLester Solbakken2018-03-071-2/+2
|/
* Put generated TensorFlow macros in replicated dirLester Solbakken2018-03-061-1/+1
|
* Put TensorFlow expression back to replicated dirLester Solbakken2018-03-061-1/+1
|
* Add testing of macro generation from stored modelLester Solbakken2018-03-051-14/+21
|
* Generate macros for TensorFlow nodes with multiple outputsLester Solbakken2018-03-052-2/+73
|
* No wildcard static importsJon Bratseth2018-03-054-8/+17
|
* Remove junit.fdramework usageJon Bratseth2018-03-0221-55/+97
|
* Add batch dimension reduction for TensorFlow importLester Solbakken2018-03-012-4/+98
|
* Merge pull request #5169 from ↵Håkon Hallingstad2018-02-283-32/+122
|\ | | | | | | | | vespa-engine/hakonhall/avoid-slobrok-in-node-admin-cluster Avoid Slobrok in node-admin cluster
| * Add testHåkon Hallingstad2018-02-282-22/+91
| |
| * Avoid Slobrok in node-admin clusterHåkon Hallingstad2018-02-281-10/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When this rolls out, two Slobroks on the node-admin will be removed, and 1 additional Slobrok will be put on one of the proxy nodes if the routing cluster has 3 or more nodes. The Orchestrator sees the latest model, i.e. expect 3 Slobroks on the proxy nodes. Since the 1 additional Slobrok service is down at the start of the rollout, only that host will be allowed to suspend among the 3. But if that 1 additional Slobrok service comes up quickly, then any of the 3 can suspend. I think this will just work - no deadlocks or similar. I couldn't find any test that would covers this code change, but will write tests if someone can help me with this, if deemed necessary.
* | Add switch to enable multiple bucket spaces in cluster controller.Geir Storli2018-02-272-5/+22
|/
* Don't validate when reloading modelsJon Bratseth2018-02-26103-486/+585
|
* Disable testsJon Bratseth2018-02-261-0/+8
|
* Disable type validation for nowJon Bratseth2018-02-261-1/+1
|
* Merge pull request #5141 from vespa-engine/bratseth/simplify-tensor-transformerJon Bratseth2018-02-2621-274/+105
|\ | | | | Bratseth/simplify tensor transformer
| * Remove printlnJon Bratseth2018-02-261-1/+0
| |
| * RefactorJon Bratseth2018-02-243-42/+13
| |
| * Remove dead codeJon Bratseth2018-02-241-163/+15
| |
| * Cleanup and more type inferenceJon Bratseth2018-02-2420-85/+94
| | | | | | | | | | | | | | - Use a type context in TensorTransformer - Correct Join.outputType - Understand tensorFromLabels and tensorFromWeightedSet - Don't wrap simple tensor arguments in constant()