Skip to content

Pull requests: llm-d/llm-d-inference-scheduler

New pull request New
24 Open 471 Closed
24 Open 471 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

perf: optimize sidecar proxy hot path for high-concurrency P/D routing
#746 opened Mar 21, 2026 by tlrmchlsmth • Draft
2 of 3 tasks
7
feat: add pending-tokens-scorer for token-aware load balancing
#745 opened Mar 21, 2026 by KaveeshKhattar Loading…
1
1
feat: precise-prefix-cache-scorer consumes tokenizer plugin
#744 opened Mar 20, 2026 by RishabhSaini Loading…
1
Remove UDS tokenizer image build from inference scheduler repo
#739 opened Mar 19, 2026 by elevran Loading…
1
1
deps(go): bump github.com/llm-d/llm-d-kv-cache from 0.6.1-0.20260317211430-786d9c8cd8f6 to 0.6.1 in the go-dependencies group across 1 directory dependencies Pull requests that update a dependency file release-note-none release notes not required
#738 opened Mar 19, 2026 by dependabot bot Loading…
test: add disruption e2e tests for scheduler failure scenarios
#735 opened Mar 18, 2026 by hexfusion Loading…
1
10
[DO_NOT_MERGE] Tracker PR for testing GIE v1.4.0-rc.3
#734 opened Mar 18, 2026 by Gregory-Pereira • Draft
Unified Disaggregate Handler hold PRs that are blocked on design, other features, release cycle, etc. lgtm "Looks good to me", indicates that a PR is ready to be merged.
#732 opened Mar 17, 2026 by roytman Loading…
70
fix: support podman-docker in e2e tests and Makefile
#730 opened Mar 17, 2026 by hexfusion Loading…
1
7
Basic implementation of dynamic LoRA adapters placement, based on shuffle sharding algorithm do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress.
#720 opened Mar 15, 2026 by dmitripikus • Draft
8
fix(test): Increase test coverage for prefix_based_pd_decider.go
#715 opened Mar 12, 2026 by gyliu513 Loading…
4
Add program aware plugin
#707 opened Mar 11, 2026 by praveingk • Draft
6
Optimize TTFT: send first token immediately after prefill for streaming
#701 opened Mar 10, 2026 by RishabhSaini Loading…
10
refactor: improve config validation in precise-prefix-cache-scorer
#690 opened Mar 9, 2026 by lisperz Loading…
Adds configuration file for sidecar proxy
#683 opened Mar 6, 2026 by DhritiShikhar Loading…
17
Align repository with llm-d repo template do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. lifecycle/stale
#649 opened Feb 24, 2026 by InfraWhisperer Loading…
1
2
Initial E/PD extension for kind deployment
#648 opened Feb 24, 2026 by revit13 • Draft
1
🌱 Standardize governance workflows, pre-commit, and remove legacy CI lifecycle/rotten
#633 opened Feb 18, 2026 by clubanderson Loading…
3 tasks
66
Enable chunked decode in the routing proxy
#603 opened Feb 9, 2026 by andreyod • Draft
2
add cookie-based affinity support lgtm "Looks good to me", indicates that a PR is ready to be merged.
#600 opened Feb 5, 2026 by roytman Loading…
1
50
Add support for responses and conversations API
#599 opened Feb 4, 2026 by asharkhan3101 Loading…
1
4
refactor(sidecar): encapsulate code better in order to share protocol implementation between different connectors
#566 opened Jan 15, 2026 by kyanokashi Loading… v0.7
50
implement context-length-aware plugin (scorer/filter)
#550 opened Jan 10, 2026 by vMaroon Loading… v0.7
56
Run unit, integration tests and builds in a container
#521 opened Dec 23, 2025 by acardace Loading… v0.7
1
24
ProTip! Add no:assignee to see everything that’s not assigned.