Skip to content

Pull requests: ROCm/iris

New pull request New
22 Open 331 Closed
22 Open 331 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

Using rocm-xio for Copy Engine in-progress We are working on it iris Iris project issue
#518 opened Apr 24, 2026 by dsidler Collaborator • Draft
Add vmem chunked allocator in-progress We are working on it iris Iris project issue
#516 opened Apr 23, 2026 by mawad-amd Collaborator • Draft
1 task done
@artulab
Add SP benchmarks for GPT-OSS-120B MoE model (GEMM+RS, RS+RMSNorm, E2E) in-progress We are working on it iris Iris project issue
#513 opened Apr 21, 2026 by aamarnat Collaborator Loading…
3 tasks
Copy Engine AG-GEMM and GEMM-AG benchmarks in-progress We are working on it iris Iris project issue
#496 opened Apr 7, 2026 by dsidler Collaborator • Draft
Add as_remote(rank) pointer translation API in-progress We are working on it iris Iris project issue
#495 opened Apr 1, 2026 by mawad-amd Collaborator • Draft
3 tasks
bench: report cross-rank timing stats in-progress We are working on it iris Iris project issue
#493 opened Apr 1, 2026 by mawad-amd Collaborator Loading…
1 of 3 tasks
6
Implement ring attention (arXiv:2310.01889)
#450 opened Mar 12, 2026 by Copilot AI • Draft
1
@mawad-amd
8
Modernize flash decode example to use torchrun pattern
#448 opened Mar 12, 2026 by Copilot AI Loading…
1
@mawad-amd
5
Implement power-of-two VMem allocator
#441 opened Mar 9, 2026 by Copilot AI • Draft
24 tasks done
1
@mawad-amd
2
Copy-engine support in-progress We are working on it iris Iris project issue
#426 opened Mar 5, 2026 by dsidler Collaborator • Draft
2
Add matmul_all_scatter op to iris.ops
#421 opened Mar 4, 2026 by Copilot AI • Draft
1
@mawad-amd
13
Port iris.x.all_to_all to Gluon with sweep benchmark, scatter plot, and assembly report
#417 opened Mar 4, 2026 by Copilot AI • Draft
1
@mawad-amd
MoE WG kernel: expose tile knobs, add benchmark tune mode, and encode bpe-based heuristic defaults
#414 opened Mar 3, 2026 by Copilot AI • Draft
@neoblizz
4
Fused MoE Optimizations
#408 opened Mar 1, 2026 by neoblizz Member Loading…
1 task done
10
Add hardware-enabled copilot runner in-progress We are working on it iris Iris project issue
#399 opened Feb 26, 2026 by JoseSantosAMD Collaborator Loading…
1 task
17
Add unified benchmarking harness (iris.bench)
#368 opened Feb 7, 2026 by Copilot AI • Draft
1
@mawad-amd
1
Fused all-gather+GEMM HBM-buffer kernel for iris.ops in-progress We are working on it iris Iris project issue
#346 opened Feb 3, 2026 by neoblizz Member Loading…
48
Add reduce_scatter and All_gather benchmark
#279 opened Nov 6, 2025 by xiaohuguo2023 Member Loading…
13
Add docker push action in-progress We are working on it iris Iris project issue
#278 opened Nov 6, 2025 by mawad-amd Collaborator Loading…
1 task
10
Add RDMA proxy thread backend in-progress We are working on it iris Iris project issue
#275 opened Oct 31, 2025 by mawad-amd Collaborator • Draft
1 task done
16
Atomic-based GEMM + ReduceScatter
#169 opened Sep 17, 2025 by danielhua23 Loading…
1
15
Implements latency test benchmarks iris Iris project issue
#114 opened Aug 21, 2025 by astroC86 Contributor • Draft
1 task done
1
24
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.