Skip to content

Pull requests: llm-d/llm-d-kv-cache

New pull request New
31 Open 342 Closed
31 Open 342 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

Support multiple gpu blocks in a single object store block size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#558 opened Apr 29, 2026 by effi-ofer Contributor Loading…
1
tests: add scheduler-integration leaf module guarding kv-cache import surface size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#557 opened Apr 29, 2026 by yankay Collaborator Loading…
2
update: remove VLLM_VERSION from makefile size/XS Denotes a PR that changes 0-9 lines, ignoring generated files.
#556 opened Apr 29, 2026 by zdtsw Contributor Loading…
1
Fix: UDS Tokenizer render error lgtm Looks good to me, indicates that a PR is ready to be merged. size/XS Denotes a PR that changes 0-9 lines, ignoring generated files.
#554 opened Apr 29, 2026 by yyzxw Loading…
1
5
Add redis lookup and improve nixl lookup size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#552 opened Apr 28, 2026 by effi-ofer Contributor Loading…
deps(go): bump go.opentelemetry.io/otel from 1.39.0 to 1.41.0 dependencies Pull requests that update a dependency file size/S Denotes a PR that changes 10-29 lines, ignoring generated files.
#541 opened Apr 24, 2026 by dependabot Bot Loading…
1
feat: Add RenderBatchCompletion RPC for multi-prompt tokenization size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#538 opened Apr 24, 2026 by albertoperdomo2 Contributor Loading…
1
update: add make target to python lint + fix lint size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#536 opened Apr 23, 2026 by zdtsw Contributor Loading…
7
fix(e2e): fix container image build platform for macOS/non-Linux hosts lgtm Looks good to me, indicates that a PR is ready to be merged. size/S Denotes a PR that changes 10-29 lines, ignoring generated files.
#535 opened Apr 23, 2026 by gyliu513 Contributor Loading…
1
3
Add Hybrid Multi-head Attention (HMA) support for KV-Cache scoring size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#533 opened Apr 19, 2026 by kapiljain1989 Loading…
1
Removed Old Helm Setup size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#530 opened Apr 19, 2026 by kapiljain1989 Loading…
1
deps(actions): bump softprops/action-gh-release from 2 to 3 dependencies Pull requests that update a dependency file size/XS Denotes a PR that changes 0-9 lines, ignoring generated files.
#516 opened Apr 14, 2026 by dependabot Bot Loading…
1
Handling Attention Group id in KV events size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#510 opened Apr 10, 2026 by kapiljain1989 Loading…
1
deps(go): bump go.opentelemetry.io/otel/sdk from 1.39.0 to 1.43.0 dependencies Pull requests that update a dependency file size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#503 opened Apr 8, 2026 by dependabot Bot Loading…
1
deps(actions): bump docker/setup-buildx-action from 3 to 4 dependencies Pull requests that update a dependency file lgtm Looks good to me, indicates that a PR is ready to be merged. lifecycle/stale size/XS Denotes a PR that changes 0-9 lines, ignoring generated files.
#501 opened Apr 7, 2026 by dependabot Bot Loading…
3
deps(actions): bump docker/build-push-action from 6 to 7 dependencies Pull requests that update a dependency file lgtm Looks good to me, indicates that a PR is ready to be merged. lifecycle/stale size/XS Denotes a PR that changes 0-9 lines, ignoring generated files.
#500 opened Apr 7, 2026 by dependabot Bot Loading…
3
feat: Add HMA support to FS connector size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#476 opened Mar 29, 2026 by kfirtoledo Collaborator • Draft
4 tasks done
1
Hybrid KV cache support for mamba+attention models
#467 opened Mar 26, 2026 by malaiwah • Draft
4 tasks done
1
9
test: Add test and usage example for mm requests lifecycle/stale size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#453 opened Mar 23, 2026 by sagearc Collaborator Loading…
2
18
fix lint errors lifecycle/stale
#446 opened Mar 23, 2026 by roytman Contributor Loading…
3
deps(go): bump google.golang.org/grpc from 1.77.0 to 1.79.3 dependencies Pull requests that update a dependency file lifecycle/rotten
#438 opened Mar 19, 2026 by dependabot Bot Loading…
6
feat:add support to invalidate KV cache via AllBlocksCleared event size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#437 opened Mar 18, 2026 by yash9263 Loading…
43
deps(go): bump the go-dependencies group across 1 directory with 16 updates dependencies Pull requests that update a dependency file size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#430 opened Mar 17, 2026 by dependabot Bot Loading…
1
feat: Add Hybrid Model Architecture (HMA) Support in Prefix-Cache Aware Scheduling lifecycle/stale size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#427 opened Mar 16, 2026 by kapiljain1989 Loading…
4
fix: Close data race in InMemoryIndex Add/Evict with RWMutex size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#422 opened Mar 16, 2026 by gyliu513 Contributor Loading…
1
4
ProTip! Updated in the last three days: updated:>2026-04-26.