Skip to content

Pull requests: openinfer-project/openinfer

New pull request New
21 Open 438 Closed
21 Open 438 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(qwen3): order cross-stream prefill temporaries in the decode-overlap path
#695 opened Jul 17, 2026 by FeathBow Collaborator Loading…
1 task done
2
[feat] qwen35: measure mixed-load ITL after chunked prefill + bench --max-batch (#470)
#693 opened Jul 16, 2026 by bbirdxr Loading…
@CAICAIIs
4
feat(qwen35): publish scheduler load snapshots
#692 opened Jul 16, 2026 by BreezyB1n Loading…
fix(qwen35): batch linear decode kernels
#690 opened Jul 16, 2026 by CAICAIIs Collaborator Loading…
1
3
fix(dsv2lite): make NCCL HTTP readiness discover wheel runtime
#684 opened Jul 15, 2026 by CAICAIIs Collaborator Loading…
docs(contributing): fix escaped markdown
#682 opened Jul 15, 2026 by Nyvo-io Loading…
5 of 8 tasks
metric(qwen3): report prefix-cache query/hit
#669 opened Jul 13, 2026 by Kokoro2336 Contributor Loading…
5 tasks done
1
1
feat(qwen35): add transactional speculative verifier
#667 opened Jul 13, 2026 by CAICAIIs Collaborator Loading…
3
feat(eagle3): drafter config, weight loading, and memory sizing
#662 opened Jul 12, 2026 by scatyf3 Contributor Loading…
7
fix(qwen3): proactive cancellation sweep for queued requests
#646 opened Jul 10, 2026 by sparkzky Contributor Loading…
7 tasks done
1
7
feat(qwen35): add opt-in DFlash speculative decoding
#626 opened Jul 9, 2026 by CAICAIIs Collaborator • Draft
8
chore: standardize model feature flags and adopt cargo-nextest as test runner
#555 opened Jul 4, 2026 by xiaguan Collaborator Loading…
docs(qwen35): draft TP2 phased design
#450 opened Jun 24, 2026 by Mrtroll486 Contributor Loading…
4 of 8 tasks
9
feat(qwen3-4b-dflash): add Qwen3-4B-DFlash draft model crate
#439 opened Jun 23, 2026 by kitty-eu-org Loading…
5 tasks done
3
feat(telemetry): add lightweight serving telemetry
#425 opened Jun 19, 2026 by ClSlaid • Draft
docs(qwen35): add prefix cache design document
#423 opened Jun 18, 2026 by Ke-Wng Contributor Loading…
5 tasks done
1
@xiaguan
6
fix(scheduler): contain worker fatal errors
#420 opened Jun 17, 2026 by ClSlaid • Draft
feat(higgs-audio): crate skeleton + config/weights + backbone forward + parity gate
#409 opened Jun 16, 2026 by ywh555hhh Contributor • Draft
1
3
PR: feat(qwen3): n-gram speculative decoding
#349 opened Jun 11, 2026 by wjinxu Contributor Loading…
@xiaguan
23
chore(qwen3): docs/dead-code cleanup — stale records, deleted-tool references, unused consts
#304 opened Jun 8, 2026 by odysa • Draft
1
feat(kernels): scaffold TVM FFI bidirectional interop test
#202 opened Jun 2, 2026 by peter941221 Contributor Loading…
5
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.