Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Babak/upgrade triton to v2.44.0 #6

Closed
wants to merge 659 commits into from
Closed
Changes from 1 commit
Commits
Show all changes
659 commits
Select commit Hold shift + click to select a range
b95366e
Update test failure messages to match Dataloader changes (#6006)
tgerdesnv Jun 30, 2023
15dbea1
Add dependency for L0_python_client_unit_tests (#6010)
GuanLuo Jul 5, 2023
20d6bb2
Improve performance tuning guide (#6026)
Tabrizian Jul 6, 2023
78d9d82
Enabling nested spans for trace mode OpenTelemetry (#5928)
oandreeva-nv Jul 7, 2023
4d864a1
Move multi-GPU dlpack test to a separate L0 test (#6001)
Tabrizian Jul 7, 2023
fd96f23
OpenVINO 2023.0.0 (#6031)
kthui Jul 7, 2023
0049763
Add test to check the output memory type for onnx models (#6033)
krishung5 Jul 7, 2023
0edd8a7
Add testing for implicit state for PyTorch backend (#6016)
Tabrizian Jul 7, 2023
bfe467c
Allow uncompressed conda execution enviroments (#6005)
jbkyang-nvi Jul 7, 2023
f431477
Fix implicit state test (#6039)
Tabrizian Jul 10, 2023
288c1df
Adding target_compile_features cxx_std_17 to tracing lib (#6040)
oandreeva-nv Jul 11, 2023
f17f348
Update 'main' to track development of 2.37.0 / 23.08
mc-nv Jul 11, 2023
ee8d048
Fix intermittent failure in L0_model_namespacing (#6052)
GuanLuo Jul 12, 2023
a8f122d
Fix PyTorch implicit model mounting in gen_qa_model_repository (#6054)
GuanLuo Jul 12, 2023
1e805ae
Fix broken links pointing to the `grpc_server.cc` file (#6068)
matemijolovic Jul 17, 2023
899fd2d
Fix L0_backend_python expected instance name (#6073)
kthui Jul 18, 2023
00fee98
Fix L0_sdk: update the search name for the client wheel (#6074)
GuanLuo Jul 19, 2023
2847211
Add GitHub action to format and lint code (#6022)
dyastremsky Jul 20, 2023
9bc9ad6
Fix default instance name change when count is 1 (#6088)
kthui Jul 21, 2023
0f84995
Add test for sequence model instance update (#5831)
kthui Jul 24, 2023
3db04cc
Fix default instance name (#6097)
kthui Jul 24, 2023
2b121fd
Removing unused tests (#6085)
oandreeva-nv Jul 25, 2023
682cc22
Update post-23.07 release (#6103)
mc-nv Jul 28, 2023
14437dc
Improve asyncio testing (#6122)
Tabrizian Jul 28, 2023
da22fd7
Reduce instance count to 1 for python bls model loading test (#6130)
krishung5 Aug 1, 2023
cfe5f24
Fix queue test to expect exact number of failures (#6133)
tanmayv25 Aug 4, 2023
36d80fe
Add CPU & GPU metrics in Grafana dashboard.json for K8s op prem deplo…
yeahdongcn Aug 4, 2023
c3a2f6b
Adding the support tracing of child models invoked from a BLS model (…
oandreeva-nv Aug 7, 2023
d964cd2
Test python environments 3.8-3.11 (#6109)
jbkyang-nvi Aug 8, 2023
09409cf
Improve L0_backend_python debugging (#6157)
krishung5 Aug 8, 2023
8a8b691
Add unreachable output test for reporting source of disconnectivity (…
GuanLuo Aug 8, 2023
82d4110
Update 'main' to track development of 2.38.0 / 23.09 (#6163)
mc-nv Aug 8, 2023
0529476
Fix the versions in the doc (#6164)
tanmayv25 Aug 9, 2023
263dec2
Update docs with NVAIE messaging (#6162)
dzier Aug 9, 2023
b5fb819
Add sanity tests for parallel instance loading (#6126)
rmccorm4 Aug 10, 2023
2265bb6
Remove extra whitespace (#6174)
dyastremsky Aug 10, 2023
4a8b716
Remove a test case that sanity checks input value of --shape CLI flag…
nv-hwoo Aug 10, 2023
ff1398c
Add test when unload/load requests for same model is received at the …
kthui Aug 14, 2023
f953f08
Make assert failures clearer in L0_trt_plugin (#6166)
dyastremsky Aug 14, 2023
d0599da
Add end-to-end CI test for decoupled model support (#6131) (#6184)
matthewkotila Aug 15, 2023
20d8c1c
Test preserve_ordering for oldest strategy sequence batcher (#6185)
rmccorm4 Aug 15, 2023
59ccf5b
added debugging guide (#5924)
tanayvarshney Aug 15, 2023
0f478f3
Add deadlock gdb section to debug guide (#6193)
rmccorm4 Aug 15, 2023
81794dd
Fix character escape in model repository documentation (#6197)
GuanLuo Aug 16, 2023
8a823b2
Fix docs test (#6192)
matthewkotila Aug 16, 2023
b02e223
Add utility functions for array manipulation (#6203)
dyastremsky Aug 17, 2023
328614e
Add gc collect to make sure gpu tensor is deallocated (#6205)
krishung5 Aug 17, 2023
7fd8516
Check for log error on failing to find explicit load model (#6204)
rmccorm4 Aug 18, 2023
47db080
Set default shm size to 1MB for Python backend (#6209)
Tabrizian Aug 22, 2023
1296c40
Trace Model Name Validation (#6199)
fpetrini15 Aug 23, 2023
fbc1f0e
Fix the check for error message (#6226)
krishung5 Aug 23, 2023
6497518
Fix copyright for debugging guide (#6225)
krishung5 Aug 23, 2023
639f758
Add watts units to GPU power metric descriptions (#6242)
rmccorm4 Aug 28, 2023
7fdff54
Update post-23.08 release (#6234)
mc-nv Aug 30, 2023
13db22e
Add tests/docs for queue size (pending request count) metric (#6233)
rmccorm4 Aug 30, 2023
b2117ab
Adding safe string to number conversions (#6173)
oandreeva-nv Aug 30, 2023
7a4ce10
Test Python execute() to return Triton error code (#6228)
kthui Sep 2, 2023
7532b76
Add docs on IPv6 (#6262)
rmccorm4 Sep 2, 2023
39ebf82
Add test for TensorRT version-compatible model support (#6255)
dyastremsky Sep 5, 2023
6a66d60
Upgrade protobuf version (#6268)
krishung5 Sep 6, 2023
6930d00
Add testing for retrieving shape and datatype in backend API (#6231)
fpetrini15 Sep 6, 2023
9fe213a
Update 'main' to track development of 2.39.0 / 23.10 (#6277)
mc-nv Sep 8, 2023
e0dc4aa
Apply UCX workaround (#6254)
Tabrizian Sep 11, 2023
41c689e
Add ensemble parameter forwarding test (#6284)
rmccorm4 Sep 11, 2023
199de7b
Exclude extra TRT version-compatible models from tests (#6294)
dyastremsky Sep 11, 2023
68e116a
Adding installation of docker and docker-buildx (#6299)
mc-nv Sep 12, 2023
7624490
Use targetmodel from header as model name in SageMaker (#6147)
nikhil-sk Sep 13, 2023
6e0a9fb
Add more error messages, return codes, and refactor HTTP server (#6297)
rmccorm4 Sep 14, 2023
3de9808
Fix typo (#6318)
krishung5 Sep 18, 2023
4a20c28
Update the request re-use example (#6283)
Tabrizian Sep 18, 2023
6527c73
Disable developer tools build for In-process API + JavaCPP tests (#6296)
jbkyang-nvi Sep 19, 2023
40c2c45
Add Python binding build. Add L0_python_api to test Python binding (#…
GuanLuo Sep 19, 2023
bbbcad7
Increase network timeout for valgrind (#6324)
krishung5 Sep 19, 2023
5dd9398
Tests and docs for ability to specify subdirectory to download for Lo…
oandreeva-nv Sep 20, 2023
2ccc3ce
Refactor HandleInfer into more readable chunks (#6332)
rmccorm4 Sep 21, 2023
e0f70aa
Refactor model generation scripts (#6336)
Tabrizian Sep 25, 2023
1f4af6d
Add testing for scalar I/O in ORT backend (#6343)
Tabrizian Sep 26, 2023
f4d4278
Update post-23.09 release (#6367)
mc-nv Sep 29, 2023
4b4f569
Add security policy (#6376)
dyastremsky Oct 3, 2023
e97ad74
Adding client-side request cancellation support and testing (#6383)
tanmayv25 Oct 4, 2023
b95736c
Add missing copyright (#6388)
tanmayv25 Oct 4, 2023
bdf227c
Add basic generate endpoints for LLM tasks (#6366)
GuanLuo Oct 6, 2023
2bf543b
Add Python backend request cancellation test (#6364)
kthui Oct 6, 2023
a33f257
Add TRT-LLM backend build to Triton (#6365) (#6392)
krishung5 Oct 7, 2023
2ca380e
Add Python backend when vLLM backend built (#6397)
dyastremsky Oct 8, 2023
60f14ac
Update build.py to build vLLM backend (#6394)
dyastremsky Oct 8, 2023
b796451
Support parameters object in generate route
nnshah1 Oct 9, 2023
135341b
Update 'main' to track development of 2.40.0 / 23.11 (#6400)
mc-nv Oct 9, 2023
b1c876d
Fix L0_sdk (#6387)
tanmayv25 Oct 11, 2023
9c707e3
Add documentation on request cancellation (#6403)
tanmayv25 Oct 11, 2023
85487a1
Fixes in request cancellation doc (#6409)
tanmayv25 Oct 11, 2023
786f48f
Document generate HTTP endpoint (#6412)
GuanLuo Oct 12, 2023
4929c33
Update SECURITY.md to not display commented copyright (#6426)
dyastremsky Oct 12, 2023
098de8f
Fix missing library in L0_data_compression (#6424)
GuanLuo Oct 12, 2023
6ae3c34
Add Javacpp-presets repo location as env variable in Java tests(#6385)
jbkyang-nvi Oct 13, 2023
e817431
TRT-LLM backend build changes (#6406)
krishung5 Oct 13, 2023
95d2ee7
Add gRPC AsyncIO request cancellation tests (#6408)
kthui Oct 13, 2023
62db791
Fix L0_implicit_state (#6427)
Tabrizian Oct 16, 2023
e11ae14
Fixing vllm build (#6433)
oandreeva-nv Oct 16, 2023
c8e4dd0
Switch Jetson model TensorRT models generation to container (#6378)
mc-nv Oct 17, 2023
960afe7
Bumped vllm version (#6444)
oandreeva-nv Oct 18, 2023
328d519
Adjust test_concurrent_same_model_load_unload_stress (#6436)
kthui Oct 18, 2023
ccdb26b
Adding emergency vllm latest release (#6454)
oandreeva-nv Oct 19, 2023
e19cfe7
Fix notify state destruction and inflight states tracking (#6451)
tanmayv25 Oct 19, 2023
c162205
Update TRT-LLM backend url (#6455)
krishung5 Oct 20, 2023
b0bff04
Added docs on python based backends (#6429)
oandreeva-nv Oct 20, 2023
35c54fd
L0_model_config Fix (#6472)
fpetrini15 Oct 24, 2023
2b1d267
Add test for Python model parameters (#6452)
kthui Oct 24, 2023
b5c2e38
Test Python BLS with different sizes of CUDA memory pool (#6276)
krishung5 Oct 25, 2023
3dfa18f
Add documentation for K8s-onprem StartupProbe (#5257)
okdimok Oct 26, 2023
2ba0762
Update `main` post-23.10 release (#6484)
mc-nv Oct 27, 2023
ed7b0fd
Adding structure reference to the new document (#6493)
mc-nv Oct 28, 2023
638fcf9
Improve L0_backend_python test stability (ensemble / gpu_tensor_lifec…
rmccorm4 Oct 30, 2023
f49493f
Add L0_generative_sequence test (#6475)
GuanLuo Nov 1, 2023
048d5ac
Downgrade vcpkg version (#6503)
GuanLuo Nov 1, 2023
d33eaa5
Collecting sub dir artifacts in GitLab yaml. Removing collect functio…
krishung5 Nov 2, 2023
b0d4612
Use post build function for TRT-LLM backend (#6476)
krishung5 Nov 2, 2023
4985ab9
Enhanced python_backend autocomplete (#6504)
oandreeva-nv Nov 2, 2023
8336873
Parse reuse-grpc-port and reuse-http-port as booleans (#6511)
dyastremsky Nov 2, 2023
f15ceec
Fixing L0_io (#6510)
oandreeva-nv Nov 3, 2023
c1b334f
Add Python-based backends CI (#6466)
pskiran1 Nov 3, 2023
4b481a6
Enabling option to restrict access to HTTP APIs based on header value…
nnshah1 Nov 3, 2023
9da5135
Upgrade DCGM from 2.4.7 to 3.2.6 (#6515)
kthui Nov 6, 2023
53b2fac
Enhance GCS credentials documentations (#6526)
kthui Nov 7, 2023
d893ca1
Test file override outside of model directory (#6516)
rmccorm4 Nov 7, 2023
0f1f924
Update ORT version to 1.16.2 (#6531)
mc-nv Nov 7, 2023
0664c5a
Adjusting expected error msg (#6517)
oandreeva-nv Nov 8, 2023
5fca835
Update 'main' to track development of 2.41.0 / 23.12 (#6543)
mc-nv Nov 8, 2023
05dae41
Enhance testing for pending request count (#6532)
tanmayv25 Nov 8, 2023
380d739
Add testing for Python backend request rescheduling (#6509)
krishung5 Nov 9, 2023
c295fbf
Check that the wget is installed (#6556)
mc-nv Nov 9, 2023
53685d3
secure deployment considerations guide (#6533)
nnshah1 Nov 10, 2023
a59f3cf
Fix typo and change the command line order (#6557)
mc-nv Nov 10, 2023
7982a53
Add error during rescheduling test to L0_generative_sequence (#6550)
GuanLuo Nov 13, 2023
a5452b4
changing references to concrete instances
nnshah1 Nov 15, 2023
e5cbe4f
Add testing for implicit state enhancements (#6524)
Tabrizian Nov 15, 2023
ee68c57
Fix copyright (#6584)
Tabrizian Nov 15, 2023
441d930
Mention TRT LLM backend supports request cancellation (#6585)
kthui Nov 16, 2023
859ab91
update model repository generation for onnx models for protobuf (#6575)
jbkyang-nvi Nov 16, 2023
4102905
Fix L0_sagemaker (#6587)
rmccorm4 Nov 16, 2023
1c20826
Add C++ server wrapper to the doc (#6592)
krishung5 Nov 16, 2023
fb5bc9f
Add timeout to client apis and tests (#6546)
jbkyang-nvi Nov 16, 2023
e7bee37
Change name generative -> iterative (#6601)
nnshah1 Nov 19, 2023
daceccf
Add documentation on generative sequence (#6595)
GuanLuo Nov 20, 2023
a5b7001
Updated description of iterative sequences
nnshah1 Nov 20, 2023
2f24070
Restricted HTTP API documentation
nnshah1 Nov 20, 2023
ba44923
Add request cancellation and debugging guide to generated docs (#6617)
rmccorm4 Nov 21, 2023
b876a90
Support for http request cancellation. Includes fix for seg fault in …
nnshah1 Nov 21, 2023
9647526
Bumped vLLM version to v0.2.2 (#6623)
oandreeva-nv Nov 21, 2023
18ee5ac
Upgrade ORT version (#6618)
tanmayv25 Nov 21, 2023
92214f7
Use compliant preprocessor (#6626)
tanmayv25 Nov 22, 2023
738996f
Update README.md (#6627)
dzier Nov 22, 2023
4b34a48
Extend request objects lifetime and fixes possible segmentation fault…
tanmayv25 Nov 22, 2023
b96ae5f
Update protobuf after python update for testing (#6638)
jbkyang-nvi Nov 29, 2023
b9f69b5
Update post-23.11 release (#6653)
mc-nv Dec 4, 2023
b44ee7c
PYBE Timeout Tests (#6483)
fpetrini15 Dec 4, 2023
4ac7f37
Add note on lack of ensemble support (#6648)
rmccorm4 Dec 5, 2023
817428a
Added request id to span attributes (#6667)
oandreeva-nv Dec 6, 2023
8afdad2
Add test for optional internal tensor within an ensemble (#6663)
GuanLuo Dec 8, 2023
a34770b
Set CMake version to 3.27.7 (#6675)
mc-nv Dec 10, 2023
cbe58e7
restore typo (#6680)
mc-nv Dec 11, 2023
f5717c6
Update 'main' to track development of 2.42.0 / 24.01 (#6673)
mc-nv Dec 12, 2023
e6c300d
iGPU build refactor (#6684) (#6691)
kthui Dec 12, 2023
f2cd999
Mlflow Plugin Fix (#6685)
fpetrini15 Dec 13, 2023
8165ca7
Fix extra content-type headers in HTTP server (#6678)
rmccorm4 Dec 13, 2023
0d2e236
Fix iGPU CMakeFile tags (#6695)
kthui Dec 13, 2023
9c56e19
adding default value for TRITON_IGPU_BUILD=OFF (#6705)
nv-kmcgill53 Dec 14, 2023
d6bd668
Add test case for decoupled model raising exception (#6686)
krishung5 Dec 15, 2023
13dd37e
Escape special characters in general docs (#6697)
nealvaidya Dec 15, 2023
2df7b25
vLLM Benchmarking Test (#6631)
pskiran1 Dec 15, 2023
23ba7a0
Allow configuring GRPC max connection age and max connection age grac…
siweili11 Dec 15, 2023
7b7ef51
Modify HTTP frontend to return error code reflecting Triton error. Ad…
GuanLuo Dec 19, 2023
121194b
Update `main` branch post-23.12 release (#6726)
mc-nv Dec 26, 2023
334d3df
trtllm CI fixes (#6687)
mc-nv Dec 28, 2023
639106e
Remove double unit test (#6714)
kthui Jan 2, 2024
854bc42
Update RE2 package location (#6750)
Tabrizian Jan 3, 2024
b42a11a
Add testing for zero tensors in PyTorch backend (#6760)
Tabrizian Jan 3, 2024
9e3bde3
Fix L0_lifecycle on insufficient hardware concurrency (#6762)
kthui Jan 4, 2024
b922b84
Simplify cmake install command (#6725)
Tabrizian Jan 5, 2024
690fe1a
Add cmdline option to set model load retry. Add test (#6764)
GuanLuo Jan 5, 2024
634e5ea
Increase timeout (#6774)
fpetrini15 Jan 8, 2024
bfb6ff0
Move from jfrog artifactory to archives.boost.io to fix boost downloa…
rmccorm4 Jan 8, 2024
0299e63
Add Triton Inference Server In-Process Python API Tests
nnshah1 Jan 11, 2024
4ffec9f
Bring back Python backend based PyTorch backend (#6518)
kthui Jan 11, 2024
0e278c1
Bump min cxx standard to 17 (#6742)
oandreeva-nv Jan 11, 2024
e58fa4c
Add tests/docs for Pinned Memory metrics (#6754)
pskiran1 Jan 12, 2024
b6a6dce
Update 'main' to track development of 2.42.0 / 24.02 (#6786)
mc-nv Jan 12, 2024
af2c54e
Support for Context Propagation for OTel trace mode (#6785)
oandreeva-nv Jan 17, 2024
7d9f6cd
Use current time when overwriting model configuration. (#6727)
whoisj Jan 17, 2024
6779fc5
Added docs for otel context propagation (#6804)
oandreeva-nv Jan 18, 2024
e74a353
Fix typos in trace.md (#6808)
rmccorm4 Jan 18, 2024
a031177
Fix test_model_config_overwite in L0_lifecycle (#6818)
GuanLuo Jan 19, 2024
37cae0c
Improve L0_backend_python on shm reliability (#6803)
kthui Jan 19, 2024
d1c8507
Remove boost::filesystem (#6810)
rmccorm4 Jan 22, 2024
2b24225
Generate unittest xml reports from L0_python_api (#6822)
rmccorm4 Jan 23, 2024
8fc7b10
Add unit test reports to L0_json, L0_metrics, L0_response_cache, L0_b…
rmccorm4 Jan 25, 2024
30d64af
Update trace summary script (#6758)
pskiran1 Jan 25, 2024
4bc15c9
Add gsutil upload retry helper function (#6817)
kthui Jan 25, 2024
b0e7e50
Add test for shutdown while unloading in background (#6835)
kthui Jan 27, 2024
f0d788b
Handle 0 dimension output for generate endpoint (#6833)
krishung5 Jan 29, 2024
62c3a76
tensorrt-llm benchmarking test (#6771)
pskiran1 Jan 29, 2024
82c5a77
Update README.md and versions post-24.01 (#6847)
mc-nv Jan 30, 2024
dfe9dde
Use libmamba solver for L0_backend_python env test. Fix pytest not fo…
krishung5 Jan 30, 2024
f345bbb
Add test for shutdown while loading model (#6837)
kthui Jan 31, 2024
8f98789
Adding OpenTelemetry Batch Span Processor (#6842)
oandreeva-nv Feb 1, 2024
9860f73
Support Double-Type Inference Request/Response Parameters (#6755)
fpetrini15 Feb 1, 2024
2623c7f
Updating vllm version to 0.3.0 (#6858)
oandreeva-nv Feb 7, 2024
bfbb24c
Python Backend Windows Support (#6830)
fpetrini15 Feb 8, 2024
3dfb7b1
Add support for Oracle Cloud in deploy (#6850)
bruno-garbaccio Feb 9, 2024
4a398b6
Add link to TRTLLM metrics docs (#6874)
rmccorm4 Feb 13, 2024
c048a9f
Add unit test reports to L0_dlpack_multi_gpu and L0_warmup (#6873)
krishung5 Feb 14, 2024
44cfb62
Set OV version to 2023.3.0 (#6880)
kthui Feb 14, 2024
fbe03b3
Fixing StringTo uint32_t used only by tracing (#6883)
oandreeva-nv Feb 14, 2024
15b7f25
Update 'main' to track development of 2.44.0 / 24.03 (#6892)
mc-nv Feb 16, 2024
d6ab1ef
Add response statistics (#6869)
kthui Feb 17, 2024
5732163
Fix busyop test for L0_memory_growth (#6900)
krishung5 Feb 22, 2024
48cf6b7
Add cancellation into response statistics (#6904)
kthui Feb 23, 2024
d0dd553
Install required pip pkgs (#6906)
krishung5 Feb 24, 2024
5630efe
Match forward headers case insensitively. (#6889)
yinggeh Feb 27, 2024
ac5ba42
Add note on --cache-config spacing and fix typos (#6929)
rmccorm4 Mar 1, 2024
ad25365
Remove ignore files that are not in use by repository (#6893)
mc-nv Mar 2, 2024
3bc6863
Update README and versions for 2.43.0 / 24.02 (#6886)
mc-nv Feb 15, 2024
5ba53d8
Set ONNX Runtime version 1.17.2
mc-nv Mar 1, 2024
46f87ff
Expose tritonserver args in values.yaml (#5582)
okyspace Mar 4, 2024
2255663
Parameterize git repository (#6934)
nv-kmcgill53 Mar 6, 2024
60071e1
Enhance bound check for shm offset (#6914)
kthui Mar 8, 2024
0a8dbaf
Allow non-decoupled model to send response and FINAL flag separately …
GuanLuo Mar 8, 2024
b603024
Add test for max queue delay timeout prompt response (#6938)
kthui Mar 8, 2024
d89e700
Test improved input validation errors (#6933)
indrajit96 Mar 9, 2024
a6ce4f6
Update Dockerfile.sdk with OpenAI support (#6941)
tgerdesnv Mar 11, 2024
79a09f2
Test Correlation Id string support for BLS (#6963)
pskiran1 Mar 11, 2024
4aba07d
Update 'main' to track development of 2.45.0 / 24.04 (#6974)
mc-nv Mar 11, 2024
55b13f6
Add AsyncIO HTTP compression test (#6975)
kthui Mar 13, 2024
30d086d
Install `genai-pa` into SDK container (#6942)
mc-nv Mar 13, 2024
de473d2
extend existing tests with more parameters (#6951)
yf711 Mar 15, 2024
06b73f3
Exposing trace context to python backend (#6985)
oandreeva-nv Mar 15, 2024
6972963
Add documentation for mapping between Triton Errors and HTTP status c…
Tabrizian Mar 19, 2024
8fadf21
Remove hatch version (#7009)
tgerdesnv Mar 21, 2024
a168d51
Update vLLM to 0.3.2 for gemma support (#6918)
kebe7jun Mar 21, 2024
4949fa2
Add missing copyright for L0_trace (#6996)
oandreeva-nv Mar 25, 2024
8c3156e
fix sphinx warnings (#7030)
yinggeh Mar 25, 2024
99240f9
Add meetup invite banner (#7049)
rmccorm4 Mar 27, 2024
6cab4bb
Update 'main' post-24.03 (#7051)
mc-nv Apr 1, 2024
3f83727
Fix incorrect version updates (#7073)
Tabrizian Apr 4, 2024
f57de7f
Update compose.py and remove mention of tensorflow1 in documentation …
jbkyang-nvi Apr 4, 2024
4018497
Merge pull request #5 from triton-inference-server/main
babakbehzad Apr 5, 2024
5ecf87a
Fix some of the problematic issues
babakbehzad Apr 5, 2024
4ba07d2
Fix another issue
babakbehzad Apr 5, 2024
6c43361
Another fix
babakbehzad Apr 5, 2024
e5ca737
Add CUDA_TOOLKIT_ROOT_DIR path
babakbehzad Apr 5, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Add CUDA_TOOLKIT_ROOT_DIR path
babakbehzad committed Apr 5, 2024
commit e5ca7373c3494760a1d71439c2be370eb44041f3
1 change: 1 addition & 0 deletions build.py
Original file line number Diff line number Diff line change
@@ -436,6 +436,7 @@ def cmake_cache_extra_args():

def core_cmake_args(components, backends, cmake_dir, install_dir):
cargs = [
cmake_core_arg("CUDA_TOOLKIT_ROOT_DIR", "PATH", "/usr/local/cuda"),
cmake_core_arg("CMAKE_BUILD_TYPE", None, FLAGS.build_type),
cmake_core_arg("CMAKE_INSTALL_PREFIX", "PATH", install_dir),
cmake_core_arg("TRITON_VERSION", "STRING", FLAGS.version),

Unchanged files with check annotations Beta

# },
"use_edit_page_button": False,
"use_issues_button": True,
"use_repository_button": True,

Check warning

Code scanning / CodeQL

Duplicate key in dict literal Warning documentation

Dictionary key 'use_repository_button' is subsequently
overwritten
.
"use_download_button": False,
"logo_only": False,
"show_toc_level": 2,
from mlflow.exceptions import MlflowException
class Config(dict):

Check warning

Code scanning / CodeQL

`__eq__` not overridden when adding attributes Warning

The class 'Config' does not override
'__eq__'
, but adds the new attribute
s3_regex
.
def __init__(self):
super().__init__()
self["triton_url"] = os.environ.get("TRITON_URL")