Skip to content

Pull requests: triton-inference-server/server

New pull request New
67 Open 710 Closed
67 Open 710 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

Reject negative TRT-LLM seed values
#8822 opened Jun 6, 2026 by fallintoplace Loading…
Reject out-of-range HTTP JSON tensor values
#8821 opened Jun 6, 2026 by fallintoplace Loading…
R25.03 shantanu
#8820 opened Jun 5, 2026 by Shantanu1058 Loading…
fix: Remove pip3 install tritonclient[all] from L0_infer install_and_test.sh
#8818 opened Jun 4, 2026 by yinggeh Contributor Loading…
1 task done
perf: Add completion queue sharding
#8815 opened Jun 3, 2026 by geobeau Loading…
3 of 22 tasks
feat: Enable PyTorch2 Batching Tests
#8814 opened Jun 2, 2026 by mattwittwer Contributor Loading…
5 of 20 tasks
@mattwittwer
feat: Add streaming tool-call parse buffer limit to prevent excessive memory usage PR: feat A new feature
#8811 opened May 31, 2026 by pskiran1 Member Loading…
8 of 20 tasks
20
security: redact OpenAI restriction secrets in logs
#8810 opened May 31, 2026 by dfgvaetyj3456356-hash Loading…
docs: explain TorchScript model.pt load failure (central directory error)
#8807 opened May 30, 2026 by mahi-mullapudi Loading…
1
fix: apply inference restriction to SageMaker MME invoke path
#8806 opened May 30, 2026 by LinZiyuu Loading…
docs: add client quickstart section (Python, C++, perf tools)
#8802 opened May 23, 2026 by Arvuno Loading…
docs: add troubleshooting section
#8799 opened May 22, 2026 by Arvuno Loading…
ci: add benchmark workflow
#8798 opened May 22, 2026 by Arvuno Loading…
docs: add AGENTS.md
#8797 opened May 22, 2026 by Arvuno Loading…
security: cap chunked HTTP request chunk count at 65536 (#8770)
#8796 opened May 22, 2026 by Arvuno Loading…
fix: Forward HTTP headers for generate requests
#8795 opened May 20, 2026 by mudit-eng Contributor • Draft
10 of 23 tasks
fix(openai-frontend): use hmac.compare_digest for restriction header value
#8788 opened May 18, 2026 by ibondarenko1 Loading…
docs: Add AGENTS.md with Cursor Cloud development instructions
#8779 opened May 13, 2026 by dzier Contributor • Draft
6 tasks done
docs: Add AGENTS.md with Cursor Cloud development environment instructions
#8778 opened May 13, 2026 by dzier Contributor • Draft
6 tasks done
docs: Add comprehensive vLLM speculative decoding documentation
#8774 opened May 11, 2026 by dzier Contributor Loading…
11 of 15 tasks
1
fix(http): return 400 for empty/invalid JSON on required HTTP bodies
#8773 opened May 10, 2026 by AffanBinFaisal Loading…
1 task
1
1
fix: mistral tool parser drops calls with leading whitespace
#8772 opened May 8, 2026 by nhodge01 Loading…
maintenance: Update grpcio Dependencies
#8765 opened May 4, 2026 by whoisj Contributor Loading…
1
fix: async model load/unload to prevent evhtp thread starvation
#8737 opened Apr 14, 2026 by itsnothuy Loading…
11 of 22 tasks
1
7
build(deps): bump pytest from 8.1.1 to 9.0.3 in /python/openai dependencies Pull requests that update a dependency file python Python related, whether backend, in-process API, client, etc
#8735 opened Apr 13, 2026 by dependabot Bot Loading…
ProTip! Filter pull requests by the default branch with base:main.