ClearML/clearml-serving
1
0
Fork 0
mirror of https://github.com/clearml/clearml-serving synced 2025-01-30 18:36:53 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
143 Commits 2 Branches 8 Tags 2.1 MiB
main
Commit Graph

80 Commits

Author SHA1 Message Date
clearml
9f51a9334f Fix torch import 2024-12-16 18:51:58 +02:00
clearml
aff27c62b8 Fix gRPC errors print stack traces and full verbose details. Add support for controlling error printouts using CLEARML_SERVING_AIO_RPC_IGNORE_ERRORS and CLEARML_SERVING_AIO_RPC_VERBOSE_ERRORS (pass a whitespace-separated list of error codes or error names) 2024-12-12 23:57:21 +02:00
IlyaMescheryakov1402
724c99c605
Add clearml_serving_inference restart on CUDA OOM (#75) 
* initial commit

* add OOM handler for MIG profiles

---------

Co-authored-by: Meshcheryakov Ilya <i.meshcheryakov@mts.ai>
 2024-07-07 15:54:08 +03:00
stephanbertl
666ce26ab2
Add exit-on-error option for tritonserver (#76) 
This fixes #60 
Co-authored-by: = <s.bertl@iaea.org>
 2024-07-07 15:51:23 +03:00
allegroai
047a120100 Fix broken requirements 2024-03-01 13:13:48 +02:00
allegroai
71c104c9df Add exception prints to serving session Task and inference Task, for better debugging capabilities 
Add report instance ID when reporting back to the main serving session task
 2024-03-01 13:13:48 +02:00
allegroai
8df521b949 Fix python < 3.10 support 
Fix custom_async engine
Suppress warning
 2024-02-27 09:45:32 +02:00
allegroai
3611a040f7 Fix requirements 2024-02-27 09:43:18 +02:00
allegroai
dc6fd46a46 Update requirements 2024-02-26 11:34:21 +02:00
allegroai
0f4122247d Fix ping serving session task to make sure everyone knows we are alive 2024-02-26 11:31:58 +02:00
allegroai
f2ba37c8d4 Fix version enabled endpoints on Triton engine were not called 2024-02-26 11:27:12 +02:00
allegroai
4ac13d5287 Fix requirements issue 2024-01-11 15:21:13 +02:00
allegroai
4335ebd340 Improve preprocess template docstring 2024-01-06 17:58:20 +02:00
allegroai
b42a0b0cfc Fix requirements 2024-01-06 17:57:50 +02:00
allegroai
368a03dc70 Fix internal ValueError exception should return 422 (not 404 as before) 2024-01-06 17:55:49 +02:00
Jake Henning
6c4bece663
Fix Pillow vulnerability "libwebp: OOB write in BuildHuffmanTable" 2023-10-04 13:23:42 +03:00
Jake Henning
c20bbd66b9
Fix Pillow vulnerability "libwebp: OOB write in BuildHuffmanTable" 2023-10-04 13:22:46 +03:00
allegroai
05cbfade2a Update requirements 2023-09-23 18:03:24 +03:00
allegroai
82ade1e24a Fix check triton config.pbtxt for missing values or colliding specifications (#62) 2023-09-23 17:42:57 +03:00
allegroai
96b335e3c2 Fix ignore auto detected platform when passing config.pbtxt with platform entry 2023-09-23 17:40:54 +03:00
allegroai
083635c803 Add str type to Triton type conversion 2023-09-23 17:36:28 +03:00
allegroai
58d826e427 Fail-safe Kafka pulling 2023-09-23 17:36:01 +03:00
allegroai
e4c07c756a Add traceback for failing to load preprocess class (#57) 2023-09-23 17:35:21 +03:00
Amir Mousavi
115770547c
Adds missing await (#55) 
Co-authored-by: Amir Mousavi <amirh@collisure.com>
 2023-05-08 12:46:52 +03:00
allegroai
fe04382fdc version bump 2023-04-12 23:39:05 +03:00
allegroai
aca8b4aa03 Upgrade to python 3.11 2023-04-12 23:38:56 +03:00
allegroai
d9599ba942 docstring 2023-04-12 23:35:00 +03:00
allegroai
78a03cc166 Register models on serving session 2023-04-12 23:34:49 +03:00
allegroai
31a4ebb965 Add CLEARML_GRPC_* environement variable support to configure grpc channel options (notice CLEARML_GRPC_var is converted into grpc.var when setting grpc channel, casing does not change) #49 2023-04-12 23:30:59 +03:00
allegroai
b16c51e631 typo 2023-04-12 23:29:15 +03:00
Victor Sonck
a04d1bda03
Remove never-used but now deprecated np.int (#42) 2023-02-07 08:05:01 +02:00
allegroai
e09e636214 version bump 2022-10-08 14:41:53 +03:00
allegroai
0c5d9820df Optimize containers 2022-10-08 02:22:32 +03:00
allegroai
395a547c04 Optimize async processing for increased speed 2022-10-08 02:12:04 +03:00
allegroai
f4aaf095a3 Add triton logging control 2022-10-08 02:10:46 +03:00
allegroai
4d4091281a add more model frameworks support 2022-10-08 02:10:34 +03:00
Aleksandar Ivanovski
d89d1370d8 [DEV] feature/bytes-payload | Add typing 2022-10-06 16:01:31 +02:00
Aleksandar Ivanovski
2aa91a3d43 [DEV] feature/bytes-payload | Handle keys when req is bytes 2022-10-06 15:13:36 +02:00
Aleksandar Ivanovski
09ed480bc2 [DEV] feature/bytes-payload | Add bytes as payload 2022-10-06 13:31:54 +02:00
allegroai
748ab67be0 version bump 2022-09-03 00:02:33 +03:00
allegroai
f4eed33f10 Add Triton support for variable length requests, adds support for HuggingFace Transformers 
Add triton_grpc_compression=False (default) for grpc connection compression control
 2022-09-02 23:41:54 +03:00
allegroai
c6c40c9a36 Add support for Preprocess class inside a module (i.e. __init__.py with subfolders) 2022-09-02 21:50:41 +03:00
allegroai
6005e238ca Add custom model serving example 2022-07-15 22:28:15 +03:00
allegroai
7fa3f2e94a Fix --aux-config not working, issue #30 2022-07-15 22:28:15 +03:00
allegroai
8a79f88040 version bump 2022-06-07 00:52:20 +03:00
allegroai
5beb077f51 Add support for update pre/post processing code to a live endpoint 2022-06-07 00:52:08 +03:00
allegroai
48f720ac91 Optimize request serving statistics reporting 2022-06-07 00:20:33 +03:00
allegroai
4a55c10366 Change default log level to warning UVICORN_LOG_LEVEL 2022-06-07 00:19:51 +03:00
allegroai
f7b21b38b1 Add CLEARML_EXTRA_PYTHON_PACKAGES for additional runtime package installaiton 
Upgrade kafka to 3.1.1
 2022-06-05 16:15:34 +03:00
allegroai
517ddc1822 Update base triton container to v22.04 (Nvidia driver version 510+) 2022-06-05 16:15:03 +03:00