data/work_threads.html

<style>
:root { color-scheme: light; }
.bi-wrap { font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; color: #1f2328 !important; }
.bi-wrap h1, .bi-wrap h2, .bi-wrap h3, .bi-wrap p, .bi-wrap strong, .bi-wrap td, .bi-wrap th, .bi-wrap div { color: #1f2328 !important; }
.bi-band { border: 1px solid #d8dee4; border-radius: 8px; background: #ffffff !important; padding: 16px; margin: 0 0 12px; }
.bi-title { display: flex; gap: 12px; align-items: flex-start; justify-content: space-between; margin-bottom: 12px; }
.bi-title h1, .bi-title h2 { margin: 0; line-height: 1.15; letter-spacing: 0; }
.bi-title h1 { font-size: 1.55rem; }
.bi-title h2 { font-size: 1.12rem; }
.bi-title p { margin: 4px 0 0; color: #57606a; max-width: 820px; }
.status-pill { border-radius: 999px; padding: 5px 9px; font-size: .78rem; font-weight: 700; background: #dafbe1; color: #116329 !important; white-space: nowrap; }
.metric-grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(138px, 1fr)); gap: 8px; }
.metric { border: 1px solid #d0d7de; border-radius: 8px; padding: 10px; background: #f6f8fa !important; min-height: 86px; }
.metric-value { font-size: 1.45rem; font-weight: 800; line-height: 1.1; color: #0969da !important; }
.metric-label { margin-top: 4px; font-size: .84rem; font-weight: 700; }
.metric-note { margin-top: 2px; font-size: .76rem; color: #57606a !important; }
.callout-grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(220px, 1fr)); gap: 8px; }
.callout { border-left: 4px solid #0969da; background: #f6f8fa !important; border-radius: 8px; padding: 10px 12px; }
.callout:nth-child(2) { border-left-color: #1a7f37; }
.callout:nth-child(3) { border-left-color: #bf8700; }
.callout:nth-child(4) { border-left-color: #cf222e; }
.callout strong { display: block; margin-bottom: 4px; }
.group-grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(310px, 1fr)); gap: 10px; }
.group-card { border: 1px solid #d8dee4; border-radius: 8px; padding: 12px; background: #fff !important; }
.group-card h3 { margin: 0 0 7px; font-size: 1rem; line-height: 1.25; letter-spacing: 0; }
.meta-row { display: flex; flex-wrap: wrap; gap: 6px; margin: 6px 0; }
.chip-row { display: inline-flex; flex-wrap: wrap; gap: 5px; align-items: center; vertical-align: middle; }
.chip { display: inline-flex; align-items: center; border: 1px solid #d0d7de; border-radius: 999px; padding: 2px 7px; font-size: .78rem; background: #f6f8fa !important; color: #24292f !important; }
.chip.bucket { border-color: #9a6700; background: #fff8c5 !important; }
.chip.kind { border-color: #0969da; background: #ddf4ff !important; }
.workflow-grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(260px, 1fr)); gap: 10px; }
.workflow-card { border: 1px solid #d8dee4; border-radius: 8px; padding: 12px; background: #fff !important; }
.workflow-card h3 { margin: 0 0 7px; font-size: 1rem; line-height: 1.25; letter-spacing: 0; }
.workflow-card .move-count { font-weight: 800; color: #0969da !important; }
.move-list { display: grid; gap: 10px; }
.move-row { border: 1px solid #d8dee4; border-radius: 8px; background: #fff !important; }
.move-row summary { list-style: none; cursor: pointer; padding: 12px; }
.move-row summary::-webkit-details-marker { display: none; }
.move-summary { display: grid; grid-template-columns: minmax(190px, 1fr) minmax(260px, 1.45fr) minmax(260px, 1.45fr) minmax(150px, .8fr) minmax(250px, 1.35fr) auto; gap: 16px; align-items: start; }
.move-title, .move-field { min-width: 0; }
.move-title h3 { margin: 0 0 4px; font-size: 1rem; line-height: 1.25; letter-spacing: 0; }
.move-field span { display: block; color: #57606a !important; font-size: .72rem; font-weight: 800; text-transform: uppercase; letter-spacing: 0; }
.move-field p { margin: 3px 0 0; font-size: .84rem; line-height: 1.35; overflow-wrap: anywhere; }
.move-field .chip, .move-title { overflow-wrap: anywhere; }
.view-bundles { align-self: center; justify-self: end; border: 1px solid #000000; border-radius: 999px; color: #000000 !important; background: #ffffff !important; padding: 4px 9px; font-size: .78rem; font-weight: 800; white-space: nowrap; }
.move-row[open] .view-bundles { background: #f6f8fa !important; }
.move-expanded { border-top: 1px solid #d8dee4; padding: 0 12px 12px; }
.bundle-row { border-top: 1px solid #eef1f4; padding: 12px 0; }
.bundle-row:first-child { border-top: none; }
.bundle-row h4 { margin: 0 0 6px; font-size: .94rem; line-height: 1.25; letter-spacing: 0; }
.bundle-scope { display: grid; grid-template-columns: repeat(auto-fit, minmax(220px, 1fr)); gap: 7px; margin-top: 8px; }
.evidence-list { margin: 8px 0 0 18px; padding: 0; color: #57606a !important; font-size: .82rem; line-height: 1.35; }
.evidence-list li { margin: 3px 0; }
.muted { color: #57606a !important; }
.evidence { font-size: .84rem; color: #57606a !important; }
.scroll-table { overflow-x: auto; border: 1px solid #d8dee4; border-radius: 8px; background: #fff !important; }
table.bi-table { width: 100%; border-collapse: collapse; font-size: .86rem; }
.bi-table th { text-align: left; background: #f6f8fa !important; color: #57606a !important; font-size: .78rem; border-bottom: 1px solid #d8dee4; padding: 8px; white-space: nowrap; }
.bi-table td { border-bottom: 1px solid #eef1f4; padding: 8px; vertical-align: top; min-width: 86px; }
.bi-table tr:last-child td { border-bottom: none; }
.wide { min-width: 280px; }
.tight { max-width: 180px; }
a { color: #0969da !important; text-decoration: none; }
a:hover { text-decoration: underline; }
.bi-wrap, .bi-wrap * { color: #000000 !important; }
@media (max-width: 720px) {
  .bi-title { display: block; }
  .status-pill { display: inline-block; margin-top: 8px; }
  .group-grid { grid-template-columns: 1fr; }
  .move-summary { grid-template-columns: 1fr; }
  .view-bundles { justify-self: start; }
}
</style>
<div class='bi-wrap'><section class='bi-band'><div class='bi-title'><div><h2>Work Threads</h2><p>Graph-connected issue/PR units with referenced context and review or CI gates attached.</p></div></div><div class='scroll-table'><table class='bi-table'><thead><tr><th>Thread</th><th>Score</th><th>Issues</th><th>PRs</th><th>Next Action</th><th>Edges</th></tr></thead><tbody><tr><td><strong>PR #188801 - [MPS] Leak MetalShaderLibrary bundled singleton to avoid exit-time destructor crashes</strong><div class='muted'>waiting on contributor</div></td><td>151</td><td><span class='chip-row'><span class='chip'>#188812</span></span></td><td><span class='chip-row'><span class='chip'>PR #188801</span></span></td><td><div class='wide'>Wait for contributor update on PR #188801; keep related issue/PR context attached.</div></td><td>1</td></tr><tr><td><strong>PR #189122 - Fix sparse-dense mul dropping data when broadcasting a size-1 sparse dim</strong><div class='muted'>ready for maintainer decision</div></td><td>139</td><td><span class='chip-row'><span class='chip'>#158861</span><span class='chip'>#188900</span></span></td><td><span class='chip-row'><span class='chip'>PR #189122</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>4</td></tr><tr><td><strong>Issue #186535 - Windows, gloo: Access violation (0xC0000005) in ProcessGroupGloo::enqueue when calling allreduce on CUDA tensors — GlooAllreduceRegistry has no kCUDA creator</strong><div class='muted'>needs design decision</div></td><td>139</td><td><span class='chip-row'><span class='chip'>#186535</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #188323 - [Inductor][CPU] dynamic=True convolution lowering crashes with ValueError: Exponent must be non-negative</strong><div class='muted'>needs design decision</div></td><td>139</td><td><span class='chip-row'><span class='chip'>#188323</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #157668 - NCCL error caused due to use of NVLS in torch 2.7.1-cu128 on aarch64 gb200 cluster</strong><div class='muted'>needs design decision</div></td><td>127</td><td><span class='chip-row'><span class='chip'>#157668</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #187912 - [CPU] Concurrent `cpublas::brgemm` calls can crash in the AMX path when the underlying oneDNN ukernel is shared</strong><div class='muted'>needs design decision</div></td><td>127</td><td><span class='chip-row'><span class='chip'>#187912</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>PR #185730 - Fix dynamic shapes for variadic kwargs</strong><div class='muted'>waiting on CI/check fix</div></td><td>121</td><td><span class='chip-row'><span class='chip'>#150022</span><span class='chip'>#150371</span></span></td><td><span class='chip-row'><span class='chip'>PR #185730</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>5</td></tr><tr><td><strong>Issue #116254 - C++ API `at::quantized_max_pool2d`: Heap-buffer-overflow</strong><div class='muted'>needs design decision</div></td><td>121</td><td><span class='chip-row'><span class='chip'>#116254</span><span class='chip'>#162476</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>1</td></tr><tr><td><strong>Issue #162422 - Runtime failure when running torch.compile() &amp; using GCC 11.5.0 on Neoverse V1</strong><div class='muted'>needs design decision</div></td><td>121</td><td><span class='chip-row'><span class='chip'>#162422</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #154297 - Hangs and timeouts on dist.reduce_scatter on B200 GPU</strong><div class='muted'>needs maintainer decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#154297</span><span class='chip'>#162178</span><span class='chip'>#162745</span><span class='chip'>#162748</span><span class='chip'>#162820</span><span class='chip'>#162871</span><span class='chip'>#162897</span><span class='chip'>#162917</span><span class='chip'>#162940</span><span class='chip'>#163429</span><span class='chip'>#165170</span><span class='chip'>#165685</span><span class='chip'>#187158</span><span class='chip'>#189065</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs maintainer decision</div></td><td>21</td></tr><tr><td><strong>Issue #55655 - Performance debugging / warning mode</strong><div class='muted'>stale/low urgency</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#55655</span><span class='chip'>#57118</span><span class='chip'>#68768</span><span class='chip'>#72948</span><span class='chip'>#75725</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>stale/low urgency</div></td><td>4</td></tr><tr><td><strong>Issue #66504 - BatchNorm runtimeError: one of the variables needed for gradient computation has been modified by an inplace operation</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#66504</span><span class='chip'>#68407</span><span class='chip'>#73332</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>3</td></tr><tr><td><strong>Issue #144965 - RuntimeError &quot;global alloc not supported yet&quot; when using TorchScript optimization.</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#69078</span><span class='chip'>#144965</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>1</td></tr><tr><td><strong>Issue #106164 - distributed.batch_isend_irecv() crash when send/recv refers to itself</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#106164</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #116423 - PyTorch Distributed Elastic Launch Segmentation Fault with Python 3.12</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#116423</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #119845 - Segmentation fault in dataloader worker sub-process</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#119845</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #145610 - mmap fails on 64k page aarch64 systems for AOTI model loading</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#145610</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #153517 - [CI][CUDA][Distributed] test_non_blocking_with_eager_init timeout</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#153517</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #162731 - DTensor cached op propagation results can be mutated when propagating other ops</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#162731</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #167693 - DISABLED test_side_stream_backward_overlap_cuda (__main__.TestAutogradStreamSynchronizationCUDA)</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#167693</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #170003 - batch_isend_irecv with nccl causes illegal memory access depending on P2P ordering</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#170003</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #173921 - [Inductor] Significant numerical divergence (4.7% relative error) in Conv2d on CPU with torch.compile</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#173921</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #174288 - [distributed] Batched isend/irecv with NCCL backend hangs on high load</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#174288</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #179502 - [DTensor] sharded view incorrectly passes when redistribution is needed</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#179502</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #180088 - [DTensor] RNG tracker does not advance state for CPU tensors on CUDA mesh, causing trunc_normal_ infinite loop</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#180088</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #183459 - Regression in torch.distributed._functional_collectives.all_to_all_single in 2.9.1 -&gt; 2.11</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#183459</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #189126 - Report a bug, as requested by the error message</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#189126</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #189144 - [XPU][B580] `flex-attn-causal` performance drop with `last_level_cache_size` cache clear between runs</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#189144</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #189150 - SIGSEGV / cudaErrorIllegalAddress when replaying a CUDA graph that captured multiple training iterations of two trainers over deeply unrolled recurrent modules</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#189150</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #189194 - [ROCm] torch 2.13 wheel: &quot;Can&#x27;t detect vectorized ISA for CPU&quot; in torch.compile smoke test on non-ROCm image (regression vs 2.12.1)</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#189194</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #189239 - [Inductor]Unable to apply layout optimization on convolution backward causes training performance regression.</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#189239</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #189281 - [CPU] operator_benchmark: embedding / embeddingbag ~70-130x slower since ~Nov 2025 (x86 + aarch64; possible measurement issue)</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#189281</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #189282 - [CPU] operator_benchmark: backward-pass (add, + batchnorm on aarch64) ~200-500x slower since ~Nov 2025 (x86 + aarch64; possible measurement artifact)</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#189282</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #71303 - [RFC] Cross-Process Performance Analysis: Straggler Detection</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#71303</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #76449 - Enhance _verify_param_shape_across_processes</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#76449</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #81684 - Message exchange failure when perform alltoallv (cpus)</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#81684</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>Issue #85088 - reentrant torch.utils.checkpoint does not work with NamedTuple outputs</strong><div class='muted'>needs design decision</div></td><td>115</td><td><span class='chip-row'><span class='chip'>#85088</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>0</td></tr><tr><td><strong>PR #186461 - Fix SymBool equality handling in symbolic shapes</strong><div class='muted'>ready for maintainer decision</div></td><td>112</td><td><span class='chip-row'><span class='chip'>#124110</span></span></td><td><span class='chip-row'><span class='chip'>PR #186461</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>1</td></tr><tr><td><strong>PR #186429 - Fix ONNX export of pad_sequence with symbolic split lengths</strong><div class='muted'>ready for maintainer decision</div></td><td>112</td><td><span class='chip-row'><span class='chip'>#127153</span></span></td><td><span class='chip-row'><span class='chip'>PR #186429</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>1</td></tr><tr><td><strong>PR #185691 - Avoid UB in float to signed integer casts</strong><div class='muted'>ready for maintainer decision</div></td><td>112</td><td><span class='chip-row'><span class='chip'>#151510</span></span></td><td><span class='chip-row'><span class='chip'>PR #185691</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>1</td></tr><tr><td><strong>PR #184716 - Fix conv_transpose2d meta output padding validation</strong><div class='muted'>ready for maintainer decision</div></td><td>112</td><td><span class='chip-row'><span class='chip'>#178127</span></span></td><td><span class='chip-row'><span class='chip'>PR #184716</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>1</td></tr><tr><td><strong>PR #188632 - Fix Dynamo opaque object staticmethod guards</strong><div class='muted'>ready for maintainer decision</div></td><td>112</td><td><span class='chip-row'><span class='chip'>#188544</span></span></td><td><span class='chip-row'><span class='chip'>PR #188632</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>3</td></tr><tr><td><strong>PR #184939 - Support SymInt steps for linspace/logspace export</strong><div class='muted'>ready for maintainer decision</div></td><td>112</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #184939</span></span></td><td><div class='wide'>ready for maintainer decision</div></td><td>0</td></tr><tr><td><strong>PR #184648 - [Test] Add has_sufficient_memory() hook to DeviceTypeTestBase</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #184648</span></span></td><td><div class='wide'>PR blocked</div></td><td>1</td></tr><tr><td><strong>PR #185882 - [PrivateUse1] Return `False` instead of `None` when PU1 backend is not available</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #185882</span></span></td><td><div class='wide'>PR blocked</div></td><td>0</td></tr><tr><td><strong>PR #186927 - [MPS] Gemv kernels</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #186927</span></span></td><td><div class='wide'>PR blocked</div></td><td>0</td></tr><tr><td><strong>PR #187501 - [Stable C Shim] Use error message retrieval shim if available at runtime</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #187501</span></span></td><td><div class='wide'>PR blocked</div></td><td>0</td></tr><tr><td><strong>PR #188237 - Optimize CSR SpMM CPU grain size and inner accumulation</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #188237</span></span></td><td><div class='wide'>PR blocked</div></td><td>1</td></tr><tr><td><strong>PR #188301 - [inductor] Fix inductor dropping ordering dep between effectful ops with different kernel types</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #188301</span></span></td><td><div class='wide'>PR blocked</div></td><td>2</td></tr><tr><td><strong>PR #189307 - [CI/CD] Copy newer CUPTI headers into manywheel binary-build images</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #189307</span></span></td><td><div class='wide'>PR blocked</div></td><td>0</td></tr><tr><td><strong>PR #189312 - [CUDA][cuBLAS] Change cuBLAS default workspace size for SM 11.0 to 32 MiB</strong><div class='muted'>waiting on CI/check fix</div></td><td>108</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #189312</span></span></td><td><div class='wide'>PR blocked</div></td><td>0</td></tr><tr><td><strong>PR #188948 - Fix triangular_solve for sparse CPU tensors on non-MKL platforms</strong><div class='muted'>waiting on contributor</div></td><td>107</td><td><span class='chip-row'><span class='chip'>#153410</span></span></td><td><span class='chip-row'><span class='chip'>PR #188948</span></span></td><td><div class='wide'>Wait for contributor update on PR #188948; keep related issue/PR context attached.</div></td><td>2</td></tr><tr><td><strong>PR #181720 - [MPS] Make pin_memory return CPU-aliased storage backed by a unified MTLBuffer</strong><div class='muted'>has linked issue</div></td><td>106</td><td><span class='chip-row'><span class='chip'>#180397</span><span class='chip'>#181374</span><span class='chip'>#188970</span></span></td><td><span class='chip-row'><span class='chip'>PR #181720</span><span class='chip'>PR #189256</span></span></td><td><div class='wide'>Review active PRs and linked issues as one maintainer work thread.</div></td><td>9</td></tr><tr><td><strong>PR #189043 - Preload full bundled cuDNN set with RTLD_GLOBAL to prevent sublibrary version mismatch</strong><div class='muted'>waiting on contributor</div></td><td>106</td><td><span class='chip-row'><span class='chip'>#188892</span></span></td><td><span class='chip-row'><span class='chip'>PR #189043</span></span></td><td><div class='wide'>Wait for contributor update on PR #189043; keep related issue/PR context attached.</div></td><td>2</td></tr><tr><td><strong>PR #135631 - [scan] Autograd</strong><div class='muted'>waiting on CI/check fix</div></td><td>100</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #135631</span></span></td><td><div class='wide'>PR blocked</div></td><td>0</td></tr><tr><td><strong>PR #188115 - [Inductor][TEST] Align `test_main_loop_scaling` with H100 support surface</strong><div class='muted'>waiting on CI/check fix</div></td><td>98</td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><span class='chip-row'><span class='chip'>PR #188115</span></span></td><td><div class='wide'>PR blocked</div></td><td>0</td></tr><tr><td><strong>Issue #103625 - DISABLED test_backward_ddp_outside (__main__.TensorPipeDdpUnderDistAutogradTest)</strong><div class='muted'>needs maintainer decision</div></td><td>97</td><td><span class='chip-row'><span class='chip'>#15963</span><span class='chip'>#16295</span><span class='chip'>#51062</span><span class='chip'>#58856</span><span class='chip'>#64093</span><span class='chip'>#69178</span><span class='chip'>#69179</span><span class='chip'>#94003</span><span class='chip'>#103625</span><span class='chip'>#104011</span><span class='chip'>#132845</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs maintainer decision</div></td><td>10</td></tr><tr><td><strong>Issue #104506 - TImeout in NCCL doesn&#x27;t work</strong><div class='muted'>stale/low urgency</div></td><td>97</td><td><span class='chip-row'><span class='chip'>#88103</span><span class='chip'>#104506</span><span class='chip'>#124950</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>stale/low urgency</div></td><td>2</td></tr><tr><td><strong>Issue #42258 - Cannot load certain function from dumped Torchscript file</strong><div class='muted'>needs design decision</div></td><td>97</td><td><span class='chip-row'><span class='chip'>#42258</span><span class='chip'>#46944</span><span class='chip'>#46946</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>2</td></tr><tr><td><strong>Issue #58111 - Static graph training fails if forward is called multiple times before backward</strong><div class='muted'>needs design decision</div></td><td>97</td><td><span class='chip-row'><span class='chip'>#58111</span><span class='chip'>#62998</span><span class='chip'>#70865</span></span></td><td><span class='chip-row'><span class='muted'>none</span></span></td><td><div class='wide'>needs triage</div></td><td>2</td></tr></tbody></table></div></section></div>