Skip to content

Pull requests: scaleapi/llm-engine

New pull request New
46 Open 703 Closed
46 Open 703 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(vllm_batch): add reasoning_parser support for batch inference
#804 opened Apr 3, 2026 by lilyz-ai Collaborator Loading…
1
fix(gcp): remove unsupported --include flags from gcloud storage rsync
#799 opened Apr 3, 2026 by arniechops Collaborator Loading…
3 tasks
1
fix(gcp): surface GCP Secret Manager errors and validate DB credentials
#793 opened Mar 31, 2026 by lilyz-ai Collaborator Loading…
3 tasks
chore: bump model-engine image tag to 4de8ad99
#789 opened Mar 27, 2026 by lilyz-ai Collaborator Loading…
2 tasks
fix(vllm): accept --disable-log-requests as no-op for vLLM 0.17+ compat
#783 opened Mar 19, 2026 by lilyz-ai Collaborator Loading…
1 task done
1
fix: map disable_log_requests to --no-enable-log-requests for newer vLLM
#779 opened Mar 11, 2026 by lilyz-ai Collaborator Loading…
2 tasks
change hook weight to -1 (job has to run after config maps placed)
#776 opened Mar 10, 2026 by masbarnes Loading…
1
Feat: Update Readme to add how to publish model engine image
#766 opened Feb 24, 2026 by postevanus-scale Collaborator Loading…
feat: add ModelWeightsManager to auto-sync HF weights on endpoint creation
#761 opened Feb 20, 2026 by lilyz-ai Collaborator Loading…
6 tasks done
15
perf improvements incl. client reuse, more efficient middleware
#759 opened Feb 15, 2026 by olliestanley Member • Draft
1
Inference: allow IPv4 bind host
#758 opened Feb 13, 2026 by dustinrubin5050 Loading…
Config: support IPv4 bind host for inference servers
#757 opened Feb 13, 2026 by dustinrubin5050 Loading…
add qwen3-8b-instruct as supported model
#756 opened Feb 12, 2026 by lukasewecker Collaborator Loading…
cpu only endpoints
#751 opened Jan 31, 2026 by dmchoiboi Collaborator Loading…
Revert openai schema back to 3.0.0
#740 opened Dec 18, 2025 by lilyz-ai Collaborator Loading…
Share controller 20251206 133239
#736 opened Dec 6, 2025 by Shreyasg13 Loading…
🚧 Add queue_message_timeout_duration parameter to endpoints (from older TASMU base commit)
#731 opened Dec 1, 2025 by ValentineDragan Contributor • Draft
[PSP-449] Add on-prem support to model-engine
#725 opened Oct 28, 2025 by TarunRavikumar Collaborator Loading…
5
[MLI-4966] Launch support multiple routes passthrough
#722 opened Oct 14, 2025 by meher-m Contributor Loading…
@meher-m
Vllm batch upgrade
#715 opened Sep 24, 2025 by dmchoiboi Collaborator • Draft
1
Add configurable queue_message_timeout_duration parameter in endpoint service configs
#709 opened Sep 16, 2025 by ValentineDragan Contributor • Draft
1
changed host flag to be 0.0.0.0 to be compatible with both ipv4 and ipv6
#707 opened Sep 12, 2025 by andytang-scale Contributor Loading…
1
Enhance model engine with max concurrency support for sync endpoints
#701 opened Aug 24, 2025 by saeidbarati-scale Loading…
on prem changes to disable cloud solutions
#700 opened Aug 18, 2025 by jen-scymanski-scale Loading…
21
multinode readme changes and remove logs
#697 opened Jun 7, 2025 by meher-m Contributor • Draft
ProTip! What’s not been updated in a month: updated:<2026-03-11.