Skip to content

Pull requests: triton-inference-server/server

New pull request New
74 Open 3,894 Closed
74 Open 3,894 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Update simple models expect simple_identity
#8091 opened Mar 22, 2025 by yinggeh Loading…
@nv-kmcgill53 @yinggeh
docs: change server README to only load densenet_onnx since tf model cannot load after 25.03 PR: docs Documentation only changes
#8089 opened Mar 22, 2025 by ziqif-nv Loading…
3
test: change simple model from tf to onnx due to tf deprecation in 25.03
#8087 opened Mar 21, 2025 by ziqif-nv • Draft
1 of 20 tasks
3
Update quickstart.md - grammar correction
#8086 opened Mar 21, 2025 by scott------ Loading…
test: avoid use TF model in L0_shared_memory due to TF deprecation PR: test Adding missing tests or correcting existing test
#8079 opened Mar 21, 2025 by ziqif-nv • Draft
6 of 20 tasks
fix: Fix gRPC cancellation race condition crash Related to server crashes, segfaults, etc.
#8078 opened Mar 20, 2025 by yinggeh Loading…
7 of 11 tasks
@yinggeh
3
fix:TensorFlow - removing obsolete scenarios
#8076 opened Mar 17, 2025 by mc-nv • Draft
[build]: Add rt_base_image parameter to differentiate triton build base image and runtime base image
#8064 opened Mar 12, 2025 by nv-tusharma • Draft
5 of 20 tasks
feat: GRPC Callback API migration for Non Inference
#8062 opened Mar 11, 2025 by indrajit96 Loading…
7 of 20 tasks
feat: Configurable grpc infer thread count PR: feat A new feature
#8061 opened Mar 10, 2025 by yinggeh Loading…
8 of 11 tasks
@yinggeh
3
feat: Add OpenAI frontend multi-LoRA model listing PR: feat A new feature
#8052 opened Mar 4, 2025 by kthui Loading…
9 of 20 tasks
@kthui
11
Build: Build using the PA binaries and whl if available.
#8043 opened Feb 27, 2025 by pvijayakrish Loading…
8 of 20 tasks
4
test: Add OpenAI frontend testing for LLM API backend PR: test Adding missing tests or correcting existing test
#8040 opened Feb 27, 2025 by krishung5 • Draft
3 of 20 tasks
12
feat: Add multi-LoRA support to OpenAI frontend PR: feat A new feature
#8038 opened Feb 26, 2025 by kthui Loading…
9 of 20 tasks
@kthui
13
build: Removed workaround to install libboost-dev. Back to apt-get install build Issues pertaining to builds
#8037 opened Feb 26, 2025 by dmitry-tokarev-nv Loading…
4 of 20 tasks
2
Adding multiple tokenizers specification for open ai frontend
#8027 opened Feb 21, 2025 by oandreeva-nv • Draft
22 tasks
ci: Fix L0_batch related flaky tests PR: ci Changes to our CI configuration files and scripts
#7999 opened Feb 10, 2025 by yinggeh Loading…
6 of 11 tasks
@yinggeh
3
docs: Remove copies of openai documentation
#7985 opened Feb 3, 2025 by statiraju Loading…
3
feat: Add graceful shutdown timer to GRPC frontend enhancement New feature or request grpc Related to the GRPC server
#7969 opened Jan 27, 2025 by mattwittwer Loading…
8 of 20 tasks
@mattwittwer
11
Separate model generation for backends on blackwell clusters
#7966 opened Jan 24, 2025 by pvijayakrish Loading…
3 of 20 tasks
@pvijayakrish
2
docs: update to fix autoscaling example command
#7883 opened Dec 16, 2024 by mattwittwer • Draft
20 tasks
refactor: Refactor of L0_backend_python and the env subtest PR: ci Changes to our CI configuration files and scripts PR: refactor A code change that neither fixes a bug nor adds a feature
#7838 opened Nov 27, 2024 by nv-kmcgill53 • Draft
5 of 20 tasks
ci: Enables testing for pull requests
#7828 opened Nov 23, 2024 by pranavm-nvidia Loading…
3 of 20 tasks
@rmccorm4
1
test: Updates L0 Python API tests to run all test files
#7827 opened Nov 23, 2024 by pranavm-nvidia Loading…
4 of 20 tasks
fix: Default max tokens to None for OpenAI frontend.
#7819 opened Nov 20, 2024 by thealmightygrant Loading…
4 of 22 tasks
2
ProTip! Follow long discussions with comments:>50.