Skip to content

Pull requests: alibaba/rtp-llm

New pull request New
88 Open 471 Closed
88 Open 471 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

Feature/refactor global info 1
#674 opened Feb 4, 2026 by wanglining97 Loading…
2
feat: use the same ports as emb engine in normal engine for arpc and grpc
#672 opened Feb 4, 2026 by zhangjianning-zjn Loading…
bugfix: update the CI result status judgment logic and adjust the pri…
#670 opened Feb 4, 2026 by guoj14 Loading…
feat: refactor global info 1/N
#669 opened Feb 4, 2026 by wanglining97 Loading…
2
feat: rocm python mtp
#668 opened Feb 3, 2026 by amd-yilizhao Loading…
1
add python atrex pa
#667 opened Feb 2, 2026 by yanglf1121 Loading…
1
feat: memory connector support hybrid kv cache
#663 opened Feb 2, 2026 by li-xiao-qing Loading…
2
feat: support hipgraph on python mode
#662 opened Feb 2, 2026 by muse-coder Loading…
3
feat: add remote_connector
#660 opened Feb 2, 2026 by MMeecatfish Loading…
18
feat: return memory cache keys
#659 opened Feb 2, 2026 by li-xiao-qing Loading…
17
fix - w13 fused
#657 opened Jan 30, 2026 by jianglan89 Loading…
1
feat: Support DeepEP dual mode for dynamic Normal/LowLatency switching in PDFusion
#655 opened Jan 30, 2026 by Zoe923 Loading…
45
[Feature] Support Per-Expert-Overlap(PEO) capability
#643 opened Jan 27, 2026 by yykzjh Loading…
8
feat: qwen2.5-vl vit amd merge gate+up, silu_and_mul
#642 opened Jan 27, 2026 by CrimsonDump Loading…
6
support per_group_fp4 weight load and fp4-moe ops
#639 opened Jan 27, 2026 by junna2016 Loading…
39
Revert "chore: rm useless device sync"
#638 opened Jan 27, 2026 by Vinkle-hzt Loading…
5
fix: refactor symm memory to avoid capture oom
#634 opened Jan 26, 2026 by JackTan25 Loading…
18
feat: support headwise attention 260126
#631 opened Jan 26, 2026 by qqbbiu Loading…
1
Feature/sm100 attention
#630 opened Jan 26, 2026 by zerozw Loading…
23
feat: add HybridKVCacheAllocator
#629 opened Jan 25, 2026 by SJTUGavinLiu Loading…
29
Feature/p2p connector
#627 opened Jan 23, 2026 by zhangchicc Loading…
fix: fix truncate token type err
#625 opened Jan 23, 2026 by wanglining97 Loading…
3
feat: use rtp-kernel fused rope kvcache ops for cuda12.9
#623 opened Jan 22, 2026 by moui0 Loading…
51
fix: fix health check error
#622 opened Jan 22, 2026 by ABNER-1 Loading…
chore: rm check for fake_stream
#614 opened Jan 21, 2026 by Vinkle-hzt Loading…
4
ProTip! Mix and match filters to narrow down what you’re looking for.