pull

Workflow runs for pull

• [CoreAI] Add multithread stress testing and shared op/model suites (#…

  queued:
  pull#100037:Commita964ac1pushedbymetascroy
  main

  Nov 3, 2026Queued
  More actions for workflow run 100037

• Qualcomm AI Engine Direct - Add composite lowering for aten.convolution_backward

  requires action with the application:
  pull#100036:Pull request#23610synchronizebyquic-xiyushi
  CodeLinaro:dev1/xiyushi/conv_backward

  Nov 3, 2026Action required
  More actions for workflow run 100036

• [CoreAI] Add multi-function export across methods and partitions

  queued:
  pull#100035:Pull request#24476openedbymetascroy
  coreai-multifunction

  Nov 3, 2026Queued
  More actions for workflow run 100035

• XNNPACK: fix enable_bf16 load failures and BatchNorm folding into a 3-D linear output

  queued:
  pull#100034:Pull request#24475openedbypytorchbot
  cherry-pick-24464-by-pytorch_bot_bot_

  Nov 3, 2026Queued
  More actions for workflow run 100034

• Vulkan: keep a reshape that changes the last dim before a quantized l…

  queued:
  pull#100033:Commit35e961epushedbySS-JIA
  main

  Nov 3, 2026Queued
  More actions for workflow run 100033

• XNNPACK: fix enable_bf16 load failures and BatchNorm folding into a 3…

  queued:
  pull#100032:Commit7bf0303pushedbyshoumikhin
  main

  Nov 3, 2026Queued
  More actions for workflow run 100032

• Vulkan: keep a reshape that changes the last dim before a quantized linear

  queued:
  pull#100031:Pull request#24116synchronizebySS-JIA
  msluszniak:ms/vulkan-qlinear-keep-input-view

  Nov 3, 2026Queued
  More actions for workflow run 100031

• [CoreAI] Rename manifest packaging to aimodel / aimodelc

  queued:
  pull#100030:Pull request#24474openedbymetascroy
  coreai-rename-packaging

  Nov 3, 2026Queued
  More actions for workflow run 100030

• Support affine int8 weight specifications in Arm quantization (#24337)

  queued:
  pull#100029:Pull request#24337synchronizebyAdithyaReddy9
  AdithyaReddy9:export-D128346146

  Nov 2, 2026Queued
  More actions for workflow run 100029

• Mark the 3-D convolution cases that fail inside a backend as expected failures

  queued:
  pull#100028:Pull request#24459synchronizebyshoumikhin
  shoumikhin:backend-suite-conv3d-xfails

  Nov 2, 2026Queued
  More actions for workflow run 100028

• Return an error from MethodMeta::get_backend_name for a delegate with…

  queued:
  pull#100027:Commit1a0ffe8pushedbymeta-codesync[bot]Bot
  main

  Nov 2, 2026Queued
  More actions for workflow run 100027

• Add boltnn_executorch_llm_runner: run weight-shared QNN LLM exports…

  queued:
  pull#100026:Commit690ace2pushedbymeta-codesync[bot]Bot
  main

  Nov 2, 2026Queued
  More actions for workflow run 100026

• [CoreAI] Add a coreai_compute_unit backend option

  queued:
  pull#100025:Pull request#24375synchronizebymetascroy
  coreai-expose-compute-unit

  Nov 2, 2026Queued
  More actions for workflow run 100025

• Keep int64 precision in portable div trunc mode and fmod

  requires action with the application:
  pull#100024:Pull request#24170synchronizebyusmanmateen
  usmanmateen:fix/int64-div-trunc-fmod

  Nov 2, 2026Action required
  More actions for workflow run 100024

• OpenVINO: fix wrong outputs when a partition returns a copy of its in…

  queued:
  pull#100023:Commit81a4666pushedbyshoumikhin
  main

  Nov 2, 2026Queued
  More actions for workflow run 100023

• Keep the attention sink and ring caches when the KV cache is quantized

  queued:
  pull#100022:Pull request#24473openedbypssrawat
  pssrawat:export-D126929701

  Nov 2, 2026Queued
  More actions for workflow run 100022

• Support affine int8 weight specifications in Arm quantization (#24337)

  cancelled:
  pull#100021:Pull request#24337synchronizebyAdithyaReddy9
  AdithyaReddy9:export-D128346146

  Nov 2, 202622m 56s
  More actions for workflow run 100021

• Separate ESP32 CI runs by commit

  queued:
  pull#100020:Pull request#24472openedbyrascani
  rascani:codex/esp32-ci-concurrency

  Nov 2, 2026Queued
  More actions for workflow run 100020

• [CoreAI] Add multithread stress testing and shared op/model suites

  queued:
  pull#100019:Pull request#24374synchronizebymetascroy
  coreai-v2/08-testing

  Nov 2, 2026Queued
  More actions for workflow run 100019

• Run Espressif operator-library cases in optimized S3 CI

  queued:
  pull#100018:Pull request#24313synchronizebyrascani
  codex/espressif-operator-library-ci

  Nov 2, 2026Queued
  More actions for workflow run 100018

• Add Espressif multiply kernel and ESP-IDF tests (#24311)

  queued:
  pull#100017:Commit77f5323pushedbyrascani
  main

  Nov 2, 2026Queued
  More actions for workflow run 100017

• Reuse committed prompt prefixes from active text requests

  queued:
  pull#100016:Pull request#24471synchronizebymergennachin
  mergennachin/active-prefix-reuse

  Nov 2, 2026Queued
  More actions for workflow run 100016

• XNNPACK: fix enable_bf16 load failures and BatchNorm folding into a 3-D linear output

  queued:
  pull#100015:Pull request#24464synchronizebyshoumikhin
  shoumikhin:xnnpack-bf16-ops

  Nov 2, 2026Queued
  More actions for workflow run 100015

• Mark the 3-D convolution cases that fail inside a backend as expected failures

  cancelled:
  pull#100014:Pull request#24459synchronizebyshoumikhin
  shoumikhin:backend-suite-conv3d-xfails

  Nov 2, 202649m 58s
  More actions for workflow run 100014

• Qualcomm AI Engine Direct - Decompose kept-whole ops that HTP leaves on CPU

  queued:
  pull#100013:Pull request#24429synchronizebyshoumikhin
  shoumikhin:qnn-htp-constant-only

  Nov 2, 2026Queued
  More actions for workflow run 100013