Skip to content

Pull requests: ovg-project/kvcached

New pull request New
53 Open 286 Closed
53 Open 286 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 capability discovery to the observability contract
#474 opened Aug 31, 2026 by ryanManocha Contributor Loading…
fix(benchmarks): init_kvcached(tp_size=...) raises TypeError in bench_map_parallelism and bench_tp_ipc
#473 opened Aug 30, 2026 by Anai-Guo Loading…
fix(vllm): bind cross-layer KV sharing layers to their target's cache
#472 opened Aug 27, 2026 by rishabhsinha17 Contributor Loading…
1
Guard get_kv_cache_manager against num_blocks beyond created FTensor capacity
#469 opened Aug 27, 2026 by rishabhsinha17 Contributor Loading…
1
3
fix(sglang): Fix SGLang SWA models 0.5.13+
#468 opened Aug 27, 2026 by jeff3071 Contributor Loading…
fix: compare resize target against current allocator capacity
#466 opened Aug 26, 2026 by jeff3071 Contributor Loading…
fix: split page create from map to avoid a remap race on Volta
#465 opened Aug 26, 2026 by andrewleech Loading…
fix(vllm): defer physical unmap until async batches complete
#464 opened Aug 23, 2026 by shipiyouniao Contributor Loading…
1
2
fix(sglang): Patch MambaSlotAllocator on sglang 0.5.13+
#459 opened Aug 21, 2026 by jeff3071 Contributor Loading…
docs: explain revisioned memory limit integration
#458 opened Aug 21, 2026 by shipiyouniao Contributor Loading…
3
feat: add kvweb rest api
#457 opened Aug 20, 2026 by allen3325 Loading…
6
perf(kv-cache): cache get_avail_physical_pages in available_size to skip per-alloc cudaMemGetInfo
#456 opened Aug 19, 2026 by SuperMarioYL Contributor Loading…
3
fix: serialize physical KV growth admission
#455 opened Aug 19, 2026 by shipiyouniao Contributor • Draft
@RixinLiu
8
fix(kv-cache): size pages via get_block_range in _get_num_alloced_blocks
#452 opened Aug 18, 2026 by SuperMarioYL Contributor Loading…
Add page-granular CPU offloading foundation
#450 opened Aug 17, 2026 by Lanoxia Contributor Loading…
Add manually triggered model compatibility matrix
#440 opened Aug 10, 2026 by Lanoxia Contributor Loading…
Fix vLLM padded KV page allocation and strides
#426 opened Aug 5, 2026 by shipiyouniao Contributor Loading…
1
3
Add automated vLLM and SGLang upstream synchronization
#423 opened Aug 4, 2026 by Lanoxia Contributor Loading…
@RixinLiu
3
Export kvcached metrics through SGLang's native endpoint
#421 opened Aug 3, 2026 by shipiyouniao Contributor Loading…
6
Add portable self-hosted GPU CI profiles gpu-ci
#420 opened Jul 31, 2026 by Lanoxia Contributor Loading…
@RixinLiu
9
fix: make KV tensor VMM batches transactional
#418 opened Jul 30, 2026 by shipiyouniao Contributor Loading…
1
15
feat(vllm): avoid CUDA context in EngineCore
#416 opened Jul 30, 2026 by shipiyouniao Contributor • Draft
16
fix(sglang): keep KV pool ownership local to each TP worker
#415 opened Jul 30, 2026 by shipiyouniao Contributor Loading…
8
fix: bind worker IPC listener to its CUDA device
#413 opened Jul 28, 2026 by shipiyouniao Contributor Loading…
9
Add KV cache operation observability
#410 opened Jul 24, 2026 by shipiyouniao Contributor Loading…
8
ProTip! no:milestone will show everything without a milestone.