[TRTLLM-17096][feat] modeling_v2: GLM-5.2 NVFP4 low-latency decode target for GB300 by xwang233 · Pull Request #20524 · NVIDIA/TensorRT-LLM

xwang233 · 2026-10-18T05:38:06Z

Dev Engineer Review

Adds GLM-5.2 NVFP4 modeling_v2 targets for SM103: TP8, TEP, and DEP.
Adds extensive CUDA, Triton, CuTe, Torch operator, dispatch, attention, MoE, speculative-decoding, KV-cache, and runtime-hook code.
Adds opt-in RuntimeHooks; default hooks remain disabled. Existing executor paths retain native behavior when hooks are absent or ineligible.
Main correctness risks are cross-rank top-k exchange, Lamport-buffer state, producer-consumer launch ordering, PDL sequencing, timeout handling, and deterministic reductions.
Main performance risks are kernel compilation, dynamic shared memory, collective workspace setup, auxiliary streams, and fallback behavior under unsupported shapes.
The change has broad integration scope. Review coverage and test adequacy remain uncertain because the supplied review assessment omitted or truncated 260 source files.
Review-finding severity counts are unavailable from the supplied evidence.

QA Engineer Review

Adds end-to-end GSM8K accuracy tests in tests/integration/defs/accuracy/modeling_v2/test_glm_moe_dsa.py for TP8, TEP4, and DEP8. Tests are restricted to SM103 and require the applicable GPU and MPI topology.
Adds CI test-list entries in:
- tests/integration/test_lists/test-db/l0_gb300_multi_gpus.yml
- tests/integration/test_lists/test-db/l0_gb300_multi_nodes_node2_gpu8.yml
The test-list entries include extended 60–90 minute timeouts and measured runtime notes.
Adds unit coverage for runtime hooks, FMHA library ordering, DSA indexer MTP/top-k helpers, and executor test stubs. These tests cover default-off behavior, fallback paths, staged metadata operations, shutdown events, and import-boundary rules.
The reported test changes replace family unit/module tests with end-to-end GSM8K gates. Engine-side runtime-hook tests remain.
The supplied evidence does not show executed test results. The full GLM suite reportedly exceeds the existing 30-minute CI timeout.
Coverage verdict: needs follow-up.

Per-File QA Perspective

cpp/tensorrt_llm/CMakeLists.txt, cpp/tensorrt_llm/kernels/CMakeLists.txt, cpp/tensorrt_llm/kernels/glmMoeDsa/CMakeLists.txt, cpp/tensorrt_llm/thop/CMakeLists.txt, and cpp/tensorrt_llm/thop/glmMoeDsa/CMakeLists.txt: Verify target inclusion, architecture selection, symbol resolution, and Torch operator linkage.
cpp/tensorrt_llm/kernels/glmMoeDsa/*: Verify SM103 support, validation errors, deterministic reductions, cross-rank synchronization, timeout behavior, PDL ordering, and invalid-input handling.
cpp/tensorrt_llm/thop/glmMoeDsa/*: Verify operator schemas, tensor validation, workspace requirements, stream behavior, fallback errors, and output shapes.
tensorrt_llm/_torch/_experimental/modeling_v2/models/glm_moe_dsa/*: Verify routing, TP8/TEP/DEP target selection, weight loading, fast-path eligibility, native fallback, dispatch installation, speculative decoding, and rank-uniform decisions.
tensorrt_llm/_torch/_experimental/modeling_v2/models/glm_moe_dsa/shared/*: Verify attention, top-k, KV append, sparse MLA, MoE, deferred normalization, draft-loop, workspace, health-check, and host-page-retention contracts.
tensorrt_llm/_torch/pyexecutor/runtime_hooks.py: Verify that all hooks remain disabled by default and that invalid hook declarations fail clearly.
tensorrt_llm/_torch/pyexecutor/engine/runners/decoder/runner.py, py_executor.py, cuda_graph_runner.py, kv_cache/kv_cache_manager_v2.py, and speculative-decoding files: Verify native behavior when hooks are absent, staging cleanup after exceptions, CUDA-graph replay, stream synchronization, and sampler-store integration.
tensorrt_llm/_torch/attention/backends/*: Verify staged metadata updates, FMHA library precedence, reused MTP rows, and unchanged native paths.
tensorrt_llm/_torch/_experimental/modeling_v2/README.md, _router_index.py, and package initializers: Verify documented target names, shared-package import rules, and resolved-mode behavior.
tests/integration/defs/accuracy/modeling_v2/test_glm_moe_dsa.py: Covers whole-model GSM8K accuracy for TP8, TEP4, and DEP8. It is listed in the GB300 CI test lists.
tests/unittest/_torch/executor/test_runtime_hooks.py: Covers runtime-hook protocols, default-off isolation, staged/native paths, and executor lifecycle integration. No integration test-list entry is expected for this unit test.
tests/unittest/_torch/attention/sparse/dsa/test_dsa_indexer.py: Covers reused top-k rows, decode filling, and MTP shared-row storage. No integration test-list entry is expected.
tests/unittest/_torch/attention/test_fmha_manager.py: Covers prepended FMHA library ordering and unavailable-library fallback. No integration test-list entry is expected.
tests/unittest/_torch/executor/test_gpu_keepalive.py and tests/unittest/_torch/executor/test_py_executor.py: Update test stubs for new executor-hook fields. No integration test-list entry is expected.
tests/unittest/_torch/modeling_v2/test_modeling_v2_claims.py: Covers family-shared import rules. No integration test-list entry is expected.
tests/integration/test_lists/test-db/*.yml: Adds GB300 CI entries for the GLM GSM8K gates with extended timeouts. Verify that the selected topology matches each test’s required rank count.

Description

Stacked on #20797. Please merge #20797 first. #20797 holds the engine side of this work
(RuntimeHooks and its call sites) so that runtime owners can review it on its own. Until it
merges, this PR's diff still contains those files, byte-identical. Please review them in #20797:

tensorrt_llm/_torch/pyexecutor/: runtime_hooks.py, py_executor.py,
engine/runners/decoder/{runner,inputs}.py

tensorrt_llm/_torch/attention/backends/: trtllm.py, fmha/manager.py,
sparse/dsa/indexer.py

their tests: tests/unittest/_torch/executor/{test_runtime_hooks,test_py_executor,test_gpu_keepalive}.py,
tests/unittest/_torch/attention/test_fmha_manager.py,
tests/unittest/_torch/attention/sparse/dsa/{test_dsa_indexer,test_indexer_gvr_prior}.py

The review scope of this PR is the new target directory, its line in the family's
routing.py, the family's csrc/CMakeLists.txt, and the tests. After #20797 merges, main is
merged here and the diff shrinks to those files.

This PR adds a GLM-5.2 NVFP4 low-latency decode target for GB300 (SM103) to modeling_v2:
models/glm_moe_dsa/glm_5_2_nvfp4__sm_103__tp8 (ModelingV2Glm52Nvfp4Sm103Tp8).

The optimization work targets one layout: attention and MoE tensor-parallel over 8 GPUs (TP8),
no attention DP, with one-model MTP-Eagle as a linear chain of five draft tokens. The family's
route() sends only that deployment to this target. Other GLM-5.2 deployments go to the other
glm_moe_dsa targets or to the built-in model:

GB300 TEP4 goes to @erictsai-nv's glm_5_2_nvfp4__sm_103__tep4 from [TRTLLM-16980][feat] modeling_v2: GLM-5.2-NVFP4 sm_103 tep4 target #20662. An earlier
revision of this PR also served TEP and DEP with a subset of its TP8 fast paths; it no longer
does, so the two targets do not overlap.
Rubin TP16 goes to glm_5_2_nvfp4__sm_107__tp16 from [None][feat] Staircase: GLM-5.2 NVFP4 low-latency decode target for Rubin (modeling_v2, TP16) #20517.
Any other deployment runs the built-in model unchanged.

routing.py keeps main's TP16 and TEP4 branches and adds the TP8 one. The NoTarget message
names all three targets.

Layout

The target follows main's target-ownership rules (test_modeling_v2_claims.py): everything it
runs lives in its own directory. Next to modeling.py and weights.py are:

the fast-path plan (dispatch.py);
the attention adoption (attention.py, attention_forward.py);
the layer composition (layers.py);
the speculative worker (spec_worker.py);
the step-loop hooks (runtime.py);
one kernel package per fast path under kernels/.

The fast paths default on inside the target. TRTLLM_STAIRCASE_GLM_LL_DISABLE=1 turns them all
off, and per-path TRTLLM_STAIRCASE_GLM_LL_* variables turn off single paths.

Executor: `RuntimeHooks` (reviewed in #20797)

The target takes over parts of the decode step through RuntimeHooks, a per-model seam that
is off by default:

executor events and an execution-stream loop;
a decode prologue that runs before the model forward.

The target also has a step-input stager and a sampler store writer
(kernels/deferred_input_prep). They are not served: #19989 on main reworked the engine paths
they hooked, so #20797 does not carry those two hooks. The code stays for a follow-up that ports
them onto the new native paths.

The target's side is runtime.py. The engine side, its tests and the note about #20306 are in
#20797.

Kernels and ops

The target's CUDA kernels and their torch ops live in its own csrc/, under the per-family
native build of #20896: one <stem>Op.cpp per <stem>.cu, declared in
models/glm_moe_dsa/csrc/CMakeLists.txt and built into libth_modeling_v2_glm_moe_dsa.so.
They register in torch.ops.mv2_glm_moe_dsa_glm_5_2_nvfp4_sm_103_tp8; the target loads them as
native_ops when routing picks it, and fake_ops.py fakes every op. Nothing under cpp/ changes.
They cover:

the post-attention hop and its routing;
the RoPE KV append;
the sparse MLA decode;
the cross-rank indexer top-k;
the dense MLP;
the draft model's routed MoE, live-row hop and tail.

Test Coverage

End-to-end accuracy gate:
tests/integration/defs/accuracy/modeling_v2/test_glm_moe_dsa.py::TestModelingV2Glm52Nvfp4Sm103Tp8::test_gsm8k_tp8.
- It serves GSM8K with modeling_v2="require", so a deployment that misses the target, or a
  step a fast path covers but cannot run, fails instead of silently falling back to the
  built-in model.
- Deployment: TP8, MTP 5, FP8 KV, TRTLLM MoE, batch 1.
- CI stage: l0_gb300_multi_nodes_node2_gpu8.
- Result: 94.35 against the reference of 90, in 34 minutes on GB300. This was measured before
  the latest merges of main; CI re-runs it on the current head.
Engine-seam tests: tests/unittest/_torch/executor/test_runtime_hooks.py and the touched
executor and attention tests cover the hooks both off (the default) and installed.
Accuracy at TP8, compared with the built-in model on the same build:
- GSM8K (1,319 questions, paired per question, two or three passes per arm): +0.34 pp
  [−0.30, +0.99].
- GPQA-diamond: 91.4 % [87.6, 94.9], in line with the model card's 89.4 %.
- MTP acceptance length per request is within ±0.12 % of the built-in model.

PR Checklist

PR description clearly explains what and why.
Follows the TRT-LLM coding guidelines.
Test cases are provided for new code paths.
No API change. The engine seam is internal and off by default; no llm_args change.
No new dependencies.
Documentation updated (modeling_v2 README).

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

Add RuntimeHooks (pyexecutor/runtime_hooks.py), a per-model seam through which a modeling_v2 target can take over parts of the decode step without changing the engine's behaviour for other models: - step-input staging, so a target can write the next step's inputs from its own buffers; - the speculative sampler's store writer; - executor events and an execution-stream loop; - a decode prologue that runs before the model forward. The executor, CUDA graph runner, decoder runner, KV cache manager V2, attention backends and the speculative modules read the hooks at their call sites. Every hook is off unless a model installs it, and the default behaviour is unchanged. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Add model-specific CUDA kernels under cpp/tensorrt_llm/kernels/glmMoeDsa/ and their torch ops under cpp/tensorrt_llm/thop/glmMoeDsa/, one <stem>Op.cpp per kernel <stem>.cu, registered as trtllm::glm_moe_dsa_<what>. They cover the decode path of GLM-5.2: the post-attention hop and its routing, the RoPE KV append, the sparse MLA decode, the cross-rank indexer top-k, the dense MLP, and the draft model's routed MoE, live-row hop and tail. The kernels build as one OBJECT library for the SM100 family and are used only by the GLM-5.2 modeling_v2 targets. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Add the glm_moe_dsa family to modeling_v2 with three targets, each claiming its own parallel topology through the family's route(): - glm_5_2_nvfp4__sm_103__tp8: tensor-parallel attention and MoE on 8 GPUs; - glm_5_2_nvfp4__sm_103__tep: tensor-parallel attention with expert-parallel experts on 4 or 8 GPUs; - glm_5_2_nvfp4__sm_103__dep: attention data parallelism with expert-parallel experts on 8 or 16 GPUs. Code the targets share (kernel packages, dispatch, attention, the layer composition, the speculative worker and the runtime-hook wiring) lives in models/glm_moe_dsa/shared/. Each target selects the fast paths it serves through its own plan; the paths default on inside the target and can be turned off with TRTLLM_STAIRCASE_GLM_LL_DISABLE or per-path TRTLLM_STAIRCASE_GLM_LL_* variables. Any configuration that no target claims runs the built-in model. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Unit tests of the glm_moe_dsa family: routing and target claims, isolation from other models, the per-target plans, the adopted layers and the runtime hooks, plus kernel tests against the native implementations. Tests that need the GLM-5.2 checkpoint find it under llm_models_root() and skip when it is not available. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Add the glm_moe_dsa family and its three targets to the modeling_v2 README. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

yuxianq · 2026-10-18T05:46:14Z

Attention assignment inactive

Checked 2026-10-29T17:09:06.492797+00:00.

The changed files no longer require trt-llm-torch-attention-devs under the target branch's CODEOWNERS. At this check, the PR has 0 attention backlog points.

There is no outstanding attention team request.

Individual review requests retained at this check:

litaotju: preserve direct code-owner review request.

Previous attention decision (inactive history)

@PerkzZheng, could you help to review this PR as trt-llm-torch-attention-devs? Thanks~

<details>
<summary>Assignment explanation</summary>

<table>
<tr><th>Components</th><td>kernels/sparse (50%); kernels/auxiliary (45%); integration/build-config (5%)</td></tr>
<tr><th>Tags</th><td>algorithm:sparse (100%); specific-algorithm:dsa (100%); representation:mla (100%); phase:decode (100%); features:rope (40%); features:quantization (40%); features:speculative-decoding (20%); context:llm (100%)</td></tr>
<tr><th>PR effort</th><td>13 points — Provisionally 13 for interacting sparse-attention kernels, early dependent launches and cross-rank transport contracts, independently of total file count. Classified as feature: the added weights.py documentation explicitly retains the built-in model&#x27;s module tree and loader, supporting optimized targets for an existing architecture.</td></tr>
<tr><th>Importance</th><td>Important — The visible contracts introduce clustered sparse-MLA softmax reduction, change RoPE/KV producer-consumer launch ordering, and fuse ordered cross-rank attention-output reduction. These require sensitive numerical, synchronization and performance review.</td></tr>
<tr><th>Retained GitHub review requests</th><td>litaotju: preserve direct code-owner review request</td></tr>
<tr><th>Affinity (0–1)</th><td>0.467 component/tag match; 0.350 after PIC preference</td></tr>
<tr><th>Outstanding points at selection</th><td>57 → 70 (+13)</td></tr>
<tr><th>Points already reserved on this PR</th><td>0</td></tr>
<tr><th>Effective weight</th><td>1</td></tr>
<tr><th>Completed review points (preceding 168 hours)</th><td>17</td></tr>
<tr><th>Combined points after assignment</th><td>87</td></tr>
<tr><th>Demand-derived target</th><td>81.00 points (soft share)</td></tr>
<tr><th>Additional fair share before assignment</th><td>7.00 points</td></tr>
<tr><th>Share explanation</th><td>Whole PR / qualification or coverage constraint exceeds a soft share; assignment is allowed.</td></tr>
<tr><th>Selection rule</th><td>affinity with 0.3-share guard</td></tr>
<tr><th>Assignment scope (PerkzZheng)</th><td>all</td></tr>
</table>

<p>Affinity and workload are snapshots at selection, not live counters. Existing reservations on this PR are counted once.</p>
</details>

…use the TP8 fast paths Each of the two targets gets a short README: the fast paths were designed and tuned for the TP8 target, these targets run the subset that applies at their topology, and both should be revisited with fast paths of their own. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

clang-format on five C++ files and one test .cu (whitespace only), an unused local and a blank line flagged by ruff, two CuTe tensor names that codespell reads as misspellings, and the prep packet's pinned slots allocated with prefer_pinned(), as the pinned-memory policy requires. The stager declines when prefer_pinned() is False, so a packet is only built when it is True. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Wanli-Jiang · 2026-10-19T09:09:08Z

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.


do we have ways to combine things into one general target like https://github.com/NVIDIA/TensorRT-LLM/pull/20267/changes did? during target distribution, we can create different targets.

Thanks, done in b209b9f. The tp8, tep and dep targets are now one target, glm_5_2_nvfp4__sm_103__default, following the #20267 convention. route() admits the same layouts as before and returns that class for all of them; the target picks the fast paths of the layout when it is built (target_paths in its modeling.py). The per-layout tables, forward and module adoption are unchanged. Only TP8 is tuned; the target README says TEP and DEP run the applicable subset and should be revisited, and a layout-specific target can be split out again later if one earns its own forward. The three GSM8K gates (tp8, tep4, dep8) pass on GB300 on the current head, after merging main.

Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

…ownership rules Main now routes sm_103 tep4 to glm_5_2_nvfp4__sm_103__tep4 (NVIDIA#20662), and its claims suite no longer lets a target import a family-level shared package. - The sm_103 low-latency target serves only the layout its fast paths were built for: attention and experts tensor-parallel over eight ranks (tp8). It is renamed glm_5_2_nvfp4__sm_103__tp8 (ModelingV2Glm52Nvfp4Sm103Tp8); the tep and dep layouts, their path sets and the dep cells are removed. - glm_moe_dsa/shared moves into the target directory: its modules beside modeling.py, its kernel packages beside the target's routed-MoE ones under kernels/. Relative imports are rewritten for the new locations. - routing.py keeps main's tp16 and tep4 branches and adds the tp8 branch. - The accuracy gate is TestModelingV2Glm52Nvfp4Sm103Tp8::test_gsm8k_tp8; the tep4 and dep8 cases and their test-list entries are removed. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Wanli-Jiang · 2026-10-29T06:16:33Z

@Wanli-Jiang Yes. All the new kernels under cpp/tensorrt_llm/kernels/glmMoeDsa/ and their ops under cpp/tensorrt_llm/thop/glmMoeDsa/ are used only by the GLM-5.2 modeling_v2 targets. Nothing outside models/glm_moe_dsa calls them.

I agree they should live with the model. #20896 gives each family its own libth_modeling_v2_<family>.so, built from models/<family>/csrc and <target>/csrc. Once it lands, we will move these kernels into models/glm_moe_dsa/.../csrc in a follow-up. The TP16 target's kernels from #20517 sit in the same directories, so we can move them in the same follow-up.

For now, I resolved the conflicts with the TP16 target in this PR. Both targets build into the existing th_common_glm_moe_dsa family, and the kernel exclude in kernels/CMakeLists.txt lists only this target's .cu files. That keeps the later move a mechanical change.

@xwang233 #20896 is merged, I think you can put the specific kernels under specific model_v2 folder now.

nvpohanh · 2026-10-29T09:20:14Z

[by Claude Code] @eopXD Could you review this PR? Thanks!

…family Move the target's CUDA kernels and torch ops from cpp/tensorrt_llm/kernels/glmMoeDsa and cpp/tensorrt_llm/thop/glmMoeDsa into glm_5_2_nvfp4__sm_103__tp8/csrc/, declared in models/glm_moe_dsa/csrc/CMakeLists.txt and built into libth_modeling_v2_glm_moe_dsa.so. The code uses the target's C++ namespace and registers into torch.ops.mv2_glm_moe_dsa_glm_5_2_nvfp4_sm_103_tp8; the target loads it as native_ops and fakes every op in fake_ops.py. Ops without tensor arguments register under CompositeExplicitAutograd so they can be faked. The modules call native_ops directly: the target package loads the library before any of them, so the checks for a missing op and the cross-rank agreement on it are gone. The development-only timing readout ops are dropped. Nothing under cpp/ changes relative to main. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

…se-pr Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

xwang233 · 2026-10-29T17:02:06Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-10-29T17:17:25Z

PR_Github #81465 [ run ] triggered by Bot. Commit: 5e4d59f Link to invocation

tensorrt-cicd · 2026-10-29T20:45:33Z

PR_Github #81465 [ run ] completed with state SUCCESS. Commit: 5e4d59f
/LLM/main/L0_MergeRequest_PR pipeline #67137 completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Either:

Wait for the PR to be fully approved — the label is added automatically once approval is complete. Having unresolved open comments is fine, or
If needed, ask a member of NVIDIA/trt-llm-ci-approvers to add the label manually.
Then re-trigger CI with the same bot command (no rebase needed).

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

Wanli-Jiang

let's do the following refactor later, merge this PR ASAP

Nothing imports it; the seam rules it recorded are in the kernel packages' docstrings and the csrc headers. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

xwang233 · 2026-10-30T21:07:19Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-10-30T21:18:02Z

PR_Github #81754 [ run ] triggered by Bot. Commit: afd1e21 Link to invocation

tensorrt-cicd · 2026-10-31T01:01:50Z

PR_Github #81754 [ run ] completed with state SUCCESS. Commit: afd1e21
/LLM/main/L0_MergeRequest_PR pipeline #67413 completed with status: 'SUCCESS'

CI Report

Link to invocation

xwang233 · 2026-10-31T01:08:47Z

/bot run --stage-list "GB300-8_GPUs-2_Nodes-PyTorch-SingleNvlinkDomain-Post-Merge-1"

tensorrt-cicd · 2026-10-31T01:16:37Z

PR_Github #81776 [ run ] triggered by Bot. Commit: afd1e21 Link to invocation

tensorrt-cicd · 2026-10-31T03:52:00Z

PR_Github #81776 [ run ] completed with state SUCCESS. Commit: afd1e21
/LLM/main/L0_MergeRequest_PR pipeline #67434 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

xwang233 · 2026-10-31T04:16:25Z

/bot skip --comment "Full pre-merge run 67413 passed and the GB300 two node post-merge stage run 67434 passed on the same commit"

tensorrt-cicd · 2026-10-31T04:22:21Z

PR_Github #81783 [ skip ] triggered by Bot. Commit: afd1e21 Link to invocation

tensorrt-cicd · 2026-10-31T04:41:18Z

PR_Github #81783 [ skip ] completed with state SUCCESS. Commit: afd1e21
Skipping testing for commit afd1e21

Link to invocation

xwang233 added 5 commits October 17, 2026 09:10

[None][doc] modeling_v2: list the GLM-5.2 targets

a87e238

Add the glm_moe_dsa family and its three targets to the modeling_v2 README. Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

xwang233 requested review from a team, Wanli-Jiang, WeiHaocheng and litaotju as code owners October 18, 2026 05:38

xwang233 requested review from VALLIS-NERIA, heyuhhh, nv-xtf, reasonsolo, schetlur-nv, thorjohnsen and zhaoyuanh-nvidia October 18, 2026 05:38

github-actions Bot assigned xwang233 Oct 18, 2026

xwang233 requested a review from Tabrizian October 18, 2026 05:40

yuxianq requested review from PerkzZheng and removed request for heyuhhh and schetlur-nv October 18, 2026 05:46

Wanli-Jiang reviewed Oct 19, 2026

View reviewed changes

xwang233 added 3 commits October 28, 2026 20:54

Merge commit 'b7b797a3aa' into modeling-v2-runtime-hooks

4b4d280

Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

Merge commit '4b4d280bc6' into glm52-ll/v3-staircase-pr

267280b

Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

xwang233 added 2 commits October 29, 2026 08:41

Merge remote-tracking branch 'upstream/main' into glm52-ll/v3-stairca…

5e4d59f

…se-pr Signed-off-by: Xiao Wang <24860335+xwang233@users.noreply.github.com>

yuxianq removed request for a team and yunruis October 29, 2026 17:08