Skip to content

Pull requests: alibaba/rtp-llm

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

feat: add gdr load mode
#851 opened Apr 1, 2026 by lixin010 Loading…
refactor: optimize broadcast
#850 opened Apr 1, 2026 by Vinkle-hzt Loading…
chore: trans logits after gemm
#849 opened Apr 1, 2026 by Vinkle-hzt Loading…
feature - add more profile scope
#848 opened Mar 31, 2026 by jianglan89 Loading…
refactor batch stream processor
#847 opened Mar 31, 2026 by xinfei-shi Loading…
feat: bailian grpc server
#846 opened Mar 31, 2026 by xinfei-shi Loading…
refactor: Fifoscheduler and GenerateStream
#844 opened Mar 31, 2026 by ZhihanYan Loading…
fix - Concurrency limit failed not return json
#843 opened Mar 30, 2026 by jianglan89 Loading…
p2p connector 实现
#839 opened Mar 27, 2026 by zhangchicc Loading…
添加CR审批检查脚本并集成到CI流程中
#838 opened Mar 27, 2026 by guoj14 Loading…
feat: support tritonPA for rocm decode
#835 opened Mar 26, 2026 by liaocz Loading…
fix: write cache store wrong gid
#833 opened Mar 26, 2026 by SJTUGavinLiu Loading…
Optimize kerenel launch
#832 opened Mar 26, 2026 by Vinkle-hzt Draft
fix: RemoteConnector HybridAttention
#831 opened Mar 26, 2026 by MMeecatfish Loading…
feat: embedding service support rdma arpc
#830 opened Mar 25, 2026 by JINGE-ui Loading…
fix: fix qwen3 next decode padding
#829 opened Mar 25, 2026 by JackTan25 Loading…
feat: use rtp-kernel fused rope kvcache ops
#824 opened Mar 23, 2026 by moui0 Loading…
Feat/fused silu quant integration
#816 opened Mar 23, 2026 by JackTan25 Loading…
add emb_dim in modelConfig
#811 opened Mar 20, 2026 by yinjuncheng Loading…
fix: 增加checkout步骤超时并优化参数配置
#810 opened Mar 20, 2026 by guoj14 Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.