Skip to content

Pull requests: triton-inference-server/vllm_backend

New pull request New
10 Open 119 Closed
10 Open 119 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
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

feat: Add GPU_DEVICE_IDS parameter support for pinning multi-GPU models to specific GPUs
#125 opened Apr 13, 2026 by pskiran1 Member Loading…
12
Fix the bge embedding model callback error
#119 opened Jan 13, 2026 by joy369 Loading…
feat: Report more vllm metrics enhancement New feature or request
#92 opened May 13, 2025 by Pavloveuge Loading…
3 of 10 tasks
@yinggeh
33
add multimodal support for qwen2.5
#90 opened May 6, 2025 by abdulazizab2 Loading…
8
Add support for priority in vllm backend
#88 opened Apr 24, 2025 by TheCodeWrangler Loading…
2 of 5 tasks
Followup with some fixes
#77 opened Dec 20, 2024 by oandreeva-nv Contributor • Draft
docs: Update README.md documentation Improvements or additions to documentation
#63 opened Sep 6, 2024 by yinggeh Contributor • Draft
@yinggeh
6
Build: Trigger CI for new vllm_backend Triton releases
#49 opened Jul 23, 2024 by nvda-mesharma Collaborator • Draft
@nvda-mesharma
17
Add input and output tokens to response
#41 opened May 16, 2024 by kebe7jun Loading…
8
Add resolve_model_relative_to_config_file config option
#29 opened Jan 22, 2024 by Legion2 Loading…
13
ProTip! Exclude everything labeled bug with -label:bug.