Skip to content

Pull requests: alibaba/rtp-llm

New pull request New
74 Open 780 Closed
74 Open 780 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

async schedule [3/N]: support async scheduler
#972 opened May 7, 2026 by Vinkle-hzt Collaborator Loading…
1
feat: sm100fp8fp4 gemm
#971 opened May 7, 2026 by qqbbiu Collaborator Loading…
5
fix(rocm): propagate hw_kernel_config to qwen35 layers
#970 opened May 7, 2026 by chengshu-lcc Collaborator Loading…
2
feat: enable Qwen35-MoE MTP && sp prefill cuda graph
#969 opened May 7, 2026 by amd-yilizhao Collaborator Loading…
3
feat: PureCP/PureDP allgather+RS routing for FP8 per-block MoE
#968 opened May 6, 2026 by intermezzi Collaborator Loading…
4
feat: add DeepGEMM JIT kernel warmup integrated into C++ engine startup
#967 opened May 6, 2026 by ydshi0 Loading…
6
feat: native setup.py and pytest (v2)
#965 opened May 5, 2026 by LLLLKKKK Collaborator Loading…
37
[WIP] Feat/dp controller master v2
#964 opened May 4, 2026 by bppps Collaborator Loading…
1
[WIP] feat: add dp controller master support (current only rr strategy)
#963 opened May 2, 2026 by bppps Collaborator Loading…
7
feat(deps): unify pip deps via PEP 503 indexes + thin requirements
#962 opened Apr 30, 2026 by LLLLKKKK Collaborator Loading…
1 of 2 tasks
26
feat - add flashinfer fp8 gemm
#961 opened Apr 30, 2026 by zerozw Collaborator Loading…
20
feat: implement CpuTpBroadcaster for CPU-only tensor broadcasting
#960 opened Apr 30, 2026 by Vinkle-hzt Collaborator Loading…
17
add input embedding for pg
#956 opened Apr 30, 2026 by parkerpang Loading…
1
fix - make prepare_cg_spec_decode_kernel easy use and understand
#954 opened Apr 29, 2026 by zerozw Collaborator Loading…
9
Qwen35 chunkgdn amd1
#950 opened Apr 29, 2026 by hxy0118 Collaborator Loading…
11
feat(p2p): 实现PD分离模式下的P2P KV Cache传输
#948 opened Apr 28, 2026 by ZhihanYan Collaborator Loading…
4
Develop/bailian
#946 opened Apr 28, 2026 by jianglan89 Collaborator Loading…
17
feat: suport hybrid pool kvcache allocator
#943 opened Apr 28, 2026 by SJTUGavinLiu Collaborator Loading…
5
mooncake support p2p connector
#941 opened Apr 27, 2026 by Vincent-Bo-ali Collaborator Loading…
4
async schedule [2/N]: support async prepare
#936 opened Apr 26, 2026 by Vinkle-hzt Collaborator Loading…
14
fix: fix rocm greedy sampling to avoid crash
#932 opened Apr 24, 2026 by liaocz Collaborator Loading…
3
feat(rocm): MoRI EP (Expert Parallelism) support for MI355X
#931 opened Apr 24, 2026 by jacobwin-ai Collaborator Loading…
6
[fix] Handle enqueue failures in RPC and API paths
#929 opened Apr 23, 2026 by ZhihanYan Collaborator Loading…
4
Develop/fix int64
#927 opened Apr 23, 2026 by xinfei-shi Collaborator Loading…
2
feat: add pre-merge-gate workflow to sync internal merge before external
#926 opened Apr 23, 2026 by guoj14 Contributor Loading…
4
ProTip! Type g i on any issue or pull request to go back to the issue listing page.