Skip to content

Pull requests: triton-inference-server/server

New pull request New
91 Open 4,213 Closed
91 Open 4,213 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

test: Add L0_backend_onnxruntime test for enabling bfloat16 dtype in ONNXRuntime backend PR: test Adding missing tests or correcting existing test
#8660 opened Feb 14, 2026 by yinggeh Loading…
4 of 10 tasks
@yinggeh
1
fix: Path Traversal Bug in SageMaker Server
#8659 opened Feb 13, 2026 by whoisj Loading…
3
Increase batcher test timeout
#8656 opened Feb 12, 2026 by mc-nv • Draft
@mc-nv
2
Add Azure Managed Identity authentication support
#8652 opened Feb 11, 2026 by nightflight-dk Loading…
12 of 22 tasks
ci: Automated document links and anchors validation PR: ci Changes to our CI configuration files and scripts
#8638 opened Feb 4, 2026 by yinggeh Loading…
5 of 11 tasks
@yinggeh
13
fix: pass http max input size to SagemakerApiServer
#8634 opened Feb 2, 2026 by a-ys Loading…
1 of 22 tasks
1
sagemaker: restrict model repository paths to configured root
#8630 opened Feb 1, 2026 by HyperPS Loading…
fix(build): Add libevent-dev dependency
#8584 opened Dec 22, 2025 by ananos Loading…
3 of 22 tasks
2
fix: comment in docker/sagemaker/serve
#8539 opened Nov 24, 2025 by kei-gnu Loading…
3 of 22 tasks
Add validation section for TensorRT models
#8531 opened Nov 21, 2025 by sreelekha-ira Loading…
1
feat: Update build.py to skip libnvshmem3-cuda-13 for cpu only build.
#8528 opened Nov 20, 2025 by Sunidhi-Gaonkar1 Loading…
4 of 22 tasks
3
fix: Fix gRPC handler thread stall on completion queue shutdown
#8495 opened Nov 6, 2025 by TheRobotCarlson Loading…
9 of 22 tasks
docs(client_guide): fix Sphinx build issues and improve Triton Python API documentation
#8491 opened Nov 5, 2025 by DHEVIKA Loading…
1
feat: support tracing option to honor parent sampling Feature
#8485 opened Oct 30, 2025 by verdie-g • Draft
7 of 22 tasks
@yinggeh
1
feat: Add Hermes tool call parser for openai compatible frontend
#8456 opened Oct 12, 2025 by amit-timalsina Loading…
11 of 12 tasks
Feat: revamp build.py CLI to improve usability and maintainability
#8437 opened Oct 2, 2025 by kpedro88 Loading…
9 of 22 tasks
4
Install libboost-dev with apt
#8416 opened Sep 26, 2025 by dmitry-tokarev-nv Loading…
feat: Minor improvements to build.py Build Issues pertaining to builds Enhancement New feature or request
#8362 opened Aug 19, 2025 by kpedro88 Loading…
6 of 22 tasks
11
fix: WAR for Python CUDA library unknown race condition PR: fix A bug fix
#8360 opened Aug 19, 2025 by GuanLuo Loading…
4
feat: add parameters in onprem k8s chart (volume, resources & env. variables)
#8324 opened Aug 1, 2025 by vladmirtxrx Loading…
3 of 22 tasks
Support tokenizer override per model for multi-model Triton + vLLM serving with OpenAI-Compatible
#8321 opened Jul 31, 2025 by JunmooByun Loading…
11 of 13 tasks
1
docs: Fix typos and grammar issues in markdown files
#8306 opened Jul 23, 2025 by cluster2600 Loading…
12 of 13 tasks
fix: mlflow plugin model deletion
#8283 opened Jul 8, 2025 by cile98 Loading…
7 of 22 tasks
fix: Fix the server runtime errors on cpu only platform and with pytorch backend
#8272 opened Jun 27, 2025 by snadampal Loading…
6 of 21 tasks
docs: fix capitalization of Triton Inference Server
#8252 opened Jun 13, 2025 by ShriyashP Loading…
5 of 13 tasks
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.