Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Pull requests: alibaba/rtp-llm

New pull request New
35 Open 186 Closed
35 Open 186 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

refactor: remove internal dependency and optimize code
#333 opened Nov 6, 2025 by sunmiaozju Loading…
feat:aiter new version #1328 update
#332 opened Nov 6, 2025 by zhiqchen-amd Loading…
refactor: optimize fp8_per_block_linear performance
#331 opened Nov 6, 2025 by yykzjh Loading…
2
feat:add rtp-simple-py-model to support run py-model standalone
#327 opened Nov 5, 2025 by Jixin10 Loading…
4
fix - add result check in device_resource get_cuda_info
#325 opened Nov 5, 2025 by alibaba-miji Loading…
feat: add memory connector
#320 opened Nov 4, 2025 by li-xiao-qing Loading…
feat: add atex cuda kernels
#319 opened Nov 4, 2025 by ZhangZhiPku Loading…
2
feat: fp8 fmha prefill
#318 opened Nov 4, 2025 by zhaoan12-prc Loading…
6
feature - add cuda version in whl name
#317 opened Nov 3, 2025 by jianglan89 Loading…
[wip]Develop/embedding grpc server
#315 opened Nov 3, 2025 by wanglining97 Loading…
8
feat: rmsnorm fuse quant and unitest
#312 opened Nov 3, 2025 by zhaoan12-prc Loading…
29
refactor: refactor cutlass groupgemm fp8
#307 opened Oct 31, 2025 by MMadhatter Loading…
feature: new mtp framework
#305 opened Oct 31, 2025 by Vinkle-hzt Loading…
3 tasks done
11
refactor: clean sampler, suppor cuda random_seed
#300 opened Oct 30, 2025 by LLLLKKKK Loading…
feat: Support the eplb feature on ROCm devices and fix some bug
#296 opened Oct 30, 2025 by Gongen-Ali Loading…
1
master refactor: remove internal dependency and optimize code
#295 opened Oct 30, 2025 by Martin7-1 Loading…
fix: [rocm] precision issues caused by the ROPE cache
#294 opened Oct 29, 2025 by liaocz Loading…
4
Features/token processor
#293 opened Oct 29, 2025 by siluzhou Loading…
feature - add reuse cache in py mla
#292 opened Oct 29, 2025 by Nancheng-11 Loading…
9
Feature/reuse_cache
#290 opened Oct 29, 2025 by zerozw Loading…
feat: support logits_index for non streaming requests
#286 opened Oct 29, 2025 by zhangjianning-zjn Loading…
feature - adapter requirement for roll
#280 opened Oct 28, 2025 by jianglan89 Loading…
2
Feature/reorder kvcache
#276 opened Oct 27, 2025 by alibaba-miji Loading…
feat: some features and optimize for rocm pymodel
#268 opened Oct 23, 2025 by liaocz Loading…
1
feat: improve pymodel bert perf
#260 opened Oct 21, 2025 by JackTan25 Loading…
ProTip! Adding no:label will show everything without a label.