All pull requests

Pull requests

• Triggered plans: other destinations, some peers, arrival groups

  in-progressiris
  #618·ariscript opened Oct 29, 2026Member·3/3·

  ·
  6

• Triggered plans: prepare the next round early, fence rounds on the device

  in-progressiris
  #617·ariscript opened Oct 29, 2026Member·2/3·

  ·
  3

• Triggered plans: one counter per chunk, per-peer completion counters

  in-progressiris
  #616·ariscript opened Oct 29, 2026Member·1/3·

  ·
  7

• Rework matmul_reduce_scatter around per-owner inboxes, with an SDMA engine

  in-progressiris
  #614·ariscript opened Oct 28, 2026Member·

  ·
  5

• chore(deps): bump actions/setup-python from 7.0.0 to 7.1.0 in the github-actions group across 1 directory

  dependenciesgithub_actionsin-progressiris
  #613·dependabot[bot] opened Oct 28, 2026Bot·

  ·

• Optimizing two-shot GEMM-AllReduce

  #610·dsidler opened Oct 27, 2026Collaborator·

  ·

• Add an all-gather on the SDMA engines

  in-progressiris
  #609·ariscript opened Oct 27, 2026Member·

  ·
  10

• chore(deps-dev): update setuptools requirement from >=84.0.0 to >=84.2.1 in the python-deps group across 1 directory

  dependenciesin-progressirispython
  #607·dependabot[bot] opened Oct 26, 2026Bot·

  ·

• Add a TDM reduce-scatter for gfx1250

  in-progressiris
  #603·nirvedhmeshram opened Oct 23, 2026Collaborator·

  ·
  5

• Add a TDM all-to-all for gfx1250

  in-progressiris
  #602·nirvedhmeshram opened Oct 23, 2026Collaborator·

  ·
  7

• Cache get_rocm_version so hipconfig runs once per process

  #595·saqibkh opened Oct 20, 2026·2 of 4 tasks·

  ·
  7

• [Fix] Run ranks on any GPU, including with vmem and SDMA

  #584·drprajap opened Oct 15, 2026Collaborator·1 task done·

  ·
  2

• Fix workspace allocation and reuse in matmul_all_reduce

  #581·MashrafeeAryan opened Oct 11, 2026·

  ·
  1

• Add a TDM all-gather and fix gfx1250 enablement

  in-progressiris
  #566·mawad-amd opened Oct 2, 2026Collaborator·

  ·

• Add iris.concurrent (concurrent, independent, fused comm+gemm)

  #544·ryanswann-amd opened Jul 23, 2026Collaborator·1 task·

  ·
  8

• MegaKernels in Iris 🔥

  in-progressiris
  #541·neoblizz opened Jun 24, 2026Member·

  ·
  6

• Support memory sharing in simulation environments

  in-progressiris
  #539·mawad-amd opened Jun 18, 2026Collaborator·1 task done·

  ·
  4

• Add more tests

  #537·micmelesse opened Jun 17, 2026Contributor·1 task·

  ·
  19

• Add vLLM Llama-70B all-reduce reproducer

  #535·micmelesse opened Jun 16, 2026Contributor·1 task·

  ·
  4

• Add graph-capturable one-shot all-reduce

  in-progressiris
  #531·mawad-amd opened May 5, 2026Collaborator·1 task done·

  ·

• Fix matmul_reduce_scatter wrapper passing unsupported bias argument

  in-progressiris
  #530·mawad-amd opened May 2, 2026Collaborator·2 tasks done·

  ·
  3

• Fix hardcoded lock value in fused GEMM+CCL operations

  in-progressiris
  #529·mawad-amd opened May 2, 2026Collaborator·3 tasks done·

  ·
  1

  7

• Cache hip.get_num_xcc() to eliminate 14ms Config overhead

  in-progressiris
  #528·mawad-amd opened May 2, 2026Collaborator·2 of 3 tasks·

  ·
  10

• Add CUDA graph capture probe for iris collectives

  in-progressiris
  #527·mawad-amd opened Apr 30, 2026Collaborator·

  ·
  5

• Validate symmetric heap placement in CCL collectives

  in-progressiris
  #526·mawad-amd opened Apr 30, 2026Collaborator·4 tasks·

  ·
  13