Skip to content

Pull requests: alibaba/rtp-llm

New pull request New
98 Open 853 Closed
98 Open 853 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(omni): add Qwen2.5-Omni multi-stage pipeline support
#1074 opened Jun 7, 2026 by stmatengss Loading…
1 of 3 tasks
5
Feat/dsv4 on dev package
#1073 opened Jun 5, 2026 by xinfei-shi Collaborator Loading…
1
feat(new_weight_loader): introduce new weight loader framework with FP8 quantization support for Qwen2
#1072 opened Jun 5, 2026 by Oneydauh Loading…
3
feat(xpu): C++ device generalization for Intel XPU support (2/4)
#1071 opened Jun 5, 2026 by aslanxie Loading…
1
perf: ensure torch inference mode throughout engine
#1070 opened Jun 5, 2026 by zhangjianning-zjn Collaborator Loading…
3
refactor(dash_sc/proxy): switch forward addr config to SERVICE_ROUTE
#1069 opened Jun 5, 2026 by sunmiaozju Collaborator Loading…
7
feat(p2p): decode_entrance P2P support with lease-based race fix
#1067 opened Jun 4, 2026 by ZhihanYan Collaborator Loading…
7 tasks
1
feat(deepepv2): 集成 DeepEPv2 ElasticBuffer 路由器
#1065 opened Jun 3, 2026 by zhijiehou Collaborator Loading…
1
Feature/dispatcher batch fanout
#1054 opened May 29, 2026 by CHW0218 Collaborator Loading…
8
feat(xpu): add Intel XPU Bazel build infrastructure
#1053 opened May 29, 2026 by aslanxie Loading…
38
fix(rocm/trt-allreduce): restore fast-path zero-copy IPC + keep exit …
#1050 opened May 28, 2026 by hxy0118 Collaborator Loading…
1
fix(stream): avoid self-deadlock in waitLoadCacheDone via reportError…
#1045 opened May 27, 2026 by ZhihanYan Collaborator Loading…
1
docs: fix typos ('comming soon', 'not suport')
#1044 opened May 27, 2026 by daqiege Loading…
1 task done
4
fix(openai): streaming spec compliance — SSE chunk split, content preservation, min_new_tokens enforcement
#1040 opened May 26, 2026 by aslanxie Loading…
18
fix(stream): wake nextOutput() waiter when stream is flipped to Error
#1036 opened May 24, 2026 by ZhihanYan Collaborator Loading…
3
Fix/dsv4 dashsc think origin
#1035 opened May 24, 2026 by jianglan89 Collaborator Loading…
4
fix(rocm): preserve column-major layout in GDN qkvz+ba fusion to fix swizzle core dump
#1030 opened May 22, 2026 by chengshu-lcc Collaborator Loading…
13
fix(dash_sc): thinking parameter propagation fixes (max_new_think_tokens, FINISH_REASON_LENGTH, 0-budget)
#1028 opened May 21, 2026 by jianglan89 Collaborator Loading…
13
feat: migrate flashinfer renorm kernel
#1027 opened May 21, 2026 by Vinkle-hzt Collaborator Loading…
1
feat(ci_gate): delegate fork PR review reruns to workflow_run helper and add pre gate
#1025 opened May 21, 2026 by guoj14 Collaborator Loading…
2
Feature/revert moriep
#1024 opened May 21, 2026 by wanglining97 Collaborator Loading…
1
Features/reuse queries
#1017 opened May 20, 2026 by siluzhou Collaborator Loading…
15
update to transformers==5.2.0
#1011 opened May 19, 2026 by HongminTan Loading…
28
feat: add ROCm aiter custom and quick allreduce support
#1010 opened May 18, 2026 by chengshu-lcc Collaborator Loading…
6
Feature/grammar logits processor
#1006 opened May 15, 2026 by wanglining97 Collaborator Loading…
11
ProTip! What’s not been updated in a month: updated:<2026-05-07.