Skip to content

Pull requests: ovg-project/kvcached

New pull request New
46 Open 249 Closed
46 Open 249 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

fix(sglang): support SGLang 0.5.13+
#411 opened Jul 24, 2026 by jeff3071 Loading…
1
Add KV cache operation observability
#410 opened Jul 24, 2026 by shipiyouniao Contributor Loading…
4
fix(controller): don't fail the losing racer of a concurrent wakeup_model() call
#409 opened Jul 23, 2026 by AmirF194 Contributor Loading…
1
2
Fix small max cached token limits
#405 opened Jul 22, 2026 by Lanoxia Loading…
1
1
Add P/D connector support matrix and smoke summaries
#404 opened Jul 22, 2026 by Lanoxia Loading…
1
Add CPU pytest CI and NIXL P/D example
#403 opened Jul 22, 2026 by Lanoxia Loading…
1
3
fix(vllm): preserve duplicate prefix cache blocks
#402 opened Jul 22, 2026 by shipiyouniao Contributor Loading…
1
2
feat(sglang): pool DeepSeek-V4 SWA KV cache
#400 opened Jul 21, 2026 by shipiyouniao Contributor • Draft
ci: fix integration branch pre-commit checks
#393 opened Jul 19, 2026 by shipiyouniao Contributor Loading…
@RixinLiu
2
fix(vllm): evict prefix-cache blocks by page to release memory (#359) good first issue Good for newcomers
#390 opened Jul 17, 2026 by ryanManocha Loading…
1
@RixinLiu
2
fix(sglang): use storage dtype for FP8 KV pools
#388 opened Jul 16, 2026 by shipiyouniao Contributor Loading…
1
12
Fix vLLM Gemma4 support by adding v2 module fallback and patch target fallback
#386 opened Jul 14, 2026 by mahendrarathore1742 Contributor Loading…
Add read-only observability snapshots
#385 opened Jul 9, 2026 by shipiyouniao Contributor Loading…
2
fix(sglang): derive free page indices on CPU
#384 opened Jul 5, 2026 by shipiyouniao Contributor Loading…
1
2
fix: make FTensor page map operations idempotent
#383 opened Jul 5, 2026 by shipiyouniao Contributor Loading…
1
1
fix(vllm): floor max cached blocks at 1 for sub-block-size budgets (#343)
#380 opened Jul 2, 2026 by SuperMarioYL Loading…
1
fix: honor explicit IPC names
#379 opened Jul 2, 2026 by shipiyouniao Contributor Loading…
1
3
Fix unsigned underflow in available physical page calculation
#377 opened Jul 2, 2026 by cmssmc00 Loading…
@RixinLiu
1
feat(sglang): account DeepSeek-V4 runtime reservations
#376 opened Jul 1, 2026 by shipiyouniao Contributor Loading…
6
fix: propagate TP and PP KV mapping failures
#373 opened Jul 1, 2026 by shipiyouniao Contributor Loading…
1
5
docs: Add comprehensive bilingual documentation with MkDocs site
#368 opened Jun 29, 2026 by tianhao909 Loading…
6 tasks done
22
Fix autopatch env handling for script-set variables
#366 opened Jun 29, 2026 by cmssmc00 Loading…
1
fix: roll back partial KV allocation on page miss
#365 opened Jun 24, 2026 by shipiyouniao Contributor Loading…
1
3
feat: support uniform cross-layer KV cache layout for CPU offloading
#361 opened Jun 15, 2026 by lianghao208 Contributor Loading…
fix map_to_kv_tensors/unmap_from_kv_tensors in MLA non-contiguous layout enhancement New feature or request
#357 opened Jun 9, 2026 by lianghao208 Contributor Loading…
@RixinLiu
1
ProTip! Follow long discussions with comments:>50.