-
Notifications
You must be signed in to change notification settings - Fork 154
Pull requests: llm-d/llm-d-inference-scheduler
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat: add approximate scoring mode with recency-weighted scoring
#808
opened Apr 9, 2026 by
bongwoobak
Contributor
Loading…
Script to automate migration for GAIE code into llm-d
#804
opened Apr 8, 2026 by
elevran
Collaborator
Loading…
migrate: import pkg/epp from gateway-api-inference-extension as pkg/epp/igw
do-not-merge/hold
Indicates that a PR should not merge because someone has issued a /hold command.
hold
PRs that are blocked on design, other features, release cycle, etc.
[feat] [cicd] Use distroless/static as default runtime base image
#795
opened Apr 2, 2026 by
elevran
Collaborator
Loading…
feat: add disaggregation decider evaluation metrics
#793
opened Apr 1, 2026 by
wenhug
Loading…
4 tasks done
Add support for s390x platform in Docker build
do-not-merge/hold
Indicates that a PR should not merge because someone has issued a /hold command.
#763
opened Mar 25, 2026 by
satyamg1620
Loading…
[cicd] Compare coverage against
main and latest release-*
#757
opened Mar 25, 2026 by
elevran
Collaborator
Loading…
[WIP] DP-aware routing with X-data-parallel-rank header injection
#750
opened Mar 22, 2026 by
satyamg1620
•
Draft
perf: optimize sidecar proxy hot path for high-concurrency P/D routing
#746
opened Mar 21, 2026 by
tlrmchlsmth
Member
Loading…
2 of 3 tasks
feat: precise-prefix-cache-scorer consumes tokenizer plugin
#744
opened Mar 20, 2026 by
RishabhSaini
Loading…
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
Contributor
•
Draft
Optimize TTFT: send first token immediately after prefill for streaming
lifecycle/stale
#701
opened Mar 10, 2026 by
RishabhSaini
Loading…
refactor: improve config validation in precise-prefix-cache-scorer
lifecycle/rotten
#690
opened Mar 9, 2026 by
lisperz
Loading…
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
Collaborator
Loading…
refactor(sidecar): encapsulate code better in order to share protocol implementation between different connectors
#566
opened Jan 15, 2026 by
kyanokashi
Contributor
Loading…
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.