Skip to content

[TRTLLM-12963][refactor] LTX-2 attention: drop dead k_pe parameter; require cached cross-attn - #14555

Merged
luyiyun1021 merged 1 commit into
NVIDIA:mainfrom
luyiyun1021:dev/ltx2-remove-k-pe
Jun 12, 2026
Merged

[TRTLLM-12963][refactor] LTX-2 attention: drop dead k_pe parameter; require cached cross-attn#14555
luyiyun1021 merged 1 commit into
NVIDIA:mainfrom
luyiyun1021:dev/ltx2-remove-k-pe

Conversation

@luyiyun1021

@luyiyun1021 luyiyun1021 commented May 26, 2026

Copy link
Copy Markdown
Collaborator

@coderabbitai summary

Description

Drop the now-dead k_pe parameter from LTX2Attention.forward and _forward_unfused, and enforce a clean cached-cross-attn invariant: cross-attn requires pre_projected_kv from project_kv. The uncached SEPARATE_QKV branch becomes self-attn-only.

Why

k_pe was the optional per-K rope override on LTX2Attention.forward — it let cross-attn pass a different rope for K than for Q. It became dead code after the earlier norm+rope fusion work moved K-rope into project_kv. That move had two goals:

  1. Eliminate the cos/sin all-gather under Ulysses — rope is per-token element-wise and commutes with seq-dim concat, so rotating K on the local shard before all-gather is bit-identical and saves a collective.
  2. Enable K-norm + K-rope to go through a single fused kernel (fused_dit_split_norm_rope) inside project_kv.

After that, every production cross-attn caller pre-rotates K via project_kv and then calls forward with pre_projected_kv=(k, v) and k_pe=None. Grep confirms zero non-None k_pe call sites. The "inline fallback when text_kv_video/text_kv_audio is None" path documented on BasicAVTransformerBlock.forward is also unreachable in production: prepare_text_cache always populates the KV list when its modality is enabled, and the block only invokes the cross-attn when the corresponding modality is enabled — so the cached KV is always present.

The old uncached SEPARATE_QKV cross-attn branch additionally had a latent silent footgun: k_pe if k_pe is not None else pe applied Q's rope to K when both came from different sources with potentially different sequence lengths.

What changed (+40 / −44, 2 files)

tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py:

  • Drop k_pe from LTX2Attention.forward and _forward_unfused.
  • Drop the k_pe=None kwargs from BasicAVTransformerBlock's a2v / v2a call sites.
  • Replace k_pe if k_pe is not None else pe in the uncached SEPARATE_QKV branch with just pe.
  • Enforce: uncached SEPARATE_QKV is self-attn-only — if context is not None: raise ValueError(...) (survives python -O, unlike assert). Cross-attn must use pre_projected_kv from project_kv. Same invariant in _forward_unfused.
  • Update BasicAVTransformerBlock.forward docstring: text_kv_video / text_kv_audio are required when the corresponding stream runs cross-attn (built by LTXModel.prepare_text_cache) — drop the "falls back to inline computation" wording.
  • Update class + project_kv docstrings to drop k_pe references.

tests/unittest/_torch/visual_gen/test_ltx2_attention.py:

  • TestLTX2CrossAttention.test_cross_attention_sanity and test_cross_attention_different_dims now use the production cached pattern: k, v = attn.project_kv(ctx, pe=...)attn(x, pre_projected_kv=(k, v), pe=...). The previous attn(x, context=ctx, pe=None) shape was exercising the unreachable inline-fallback path and is now rejected.

Test Coverage

Local on B200, wt-3 container:

  • tests/unittest/_torch/visual_gen/test_ltx2_attention.py6/6 PASS
  • tests/unittest/_torch/visual_gen/test_ltx2_transformer.py14/14 PASS

No production behavior change.

PR Checklist

  • PR description clearly explains what and why.

  • PR Follows TRT-LLM CODING GUIDELINES.

  • Test cases are provided for new code paths.

  • Any new dependencies have been scanned for license and vulnerabilities.

  • CODEOWNERS updated if ownership changes.

  • Documentation updated as needed.

  • Update tava architecture diagram if significant design change.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

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

@luyiyun1021
luyiyun1021 requested a review from a team as a code owner May 26, 2026 06:27
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@coderabbitai

coderabbitai Bot commented May 26, 2026

Copy link
Copy Markdown
Contributor
📝 Walkthrough

Walkthrough

The PR removes the redundant k_pe parameter from LTX2Attention.forward() and standardizes on pre_projected_kv to signal upstream-rotated K/V tensors. Method signatures and docstrings are updated to clarify Q/K/V+PE invariants, call sites in BasicAVTransformerBlock are adjusted to remove k_pe=None, and unit tests are aligned to the production calling pattern using project_kv().

Changes

Removing k_pe parameter and standardizing on pre_projected_kv

Layer / File(s) Summary
Contract updates and documentation clarification
tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py
Class docstring, project_kv() contract, and forward() signature/docstring are updated to document that returned K is already rotated, downstream callers must pass it via pre_projected_kv, and the new FUSE_QKV vs SEPARATE_QKV caller behavior expectations.
Core Q/K/V invariant enforcement in SEPARATE_QKV
tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py
SEPARATE_QKV handling rewritten to enforce: when pre_projected_kv is present, K/V come from cached projections and only Q receives RMSNorm+optional RoPE; when absent, assertion requires context is None (self-attention only), and Q/K/V are computed from x with RoPE applied to both.
Fallback path alignment and RoPE logic
tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py
_forward_unfused() signature and docstring remove k_pe parameter; RoPE application logic removes the k_pe-specific branch, maintaining only pre_projected_kv-dependent behavior.
Cross-attention call site updates in BasicAVTransformerBlock
tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py
Audio→video and video→audio cross-attention calls remove the now-invalid k_pe=None argument while retaining pre_projected_kv=(k, v) and pe=... parameters.
Test updates to production calling pattern
tests/unittest/_torch/visual_gen/test_ltx2_attention.py
Cross-attention unit tests are updated to call attn.project_kv(ctx, pe=None) to obtain pre-projected (k, v) and then call attn with pre_projected_kv=(k, v), replacing the direct context=ctx argument.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Docstring Coverage ✅ Passed Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
Description check ✅ Passed The PR description is comprehensive and well-structured, following the template with clear sections for Description, Test Coverage, and a completed PR Checklist. It thoroughly explains the rationale, changes, and test coverage.
Title check ✅ Passed The title clearly describes the main change: removing the k_pe parameter from LTX-2 attention and requiring cached cross-attention, which aligns with the PR's primary objectives.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands and usage tips.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🧹 Nitpick comments (2)
tests/unittest/_torch/visual_gen/test_ltx2_attention.py (1)

193-199: ⚡ Quick win

Add a negative test for the newly enforced uncached cross-attention invariant.

Line 197 and Line 238 validate the new cached cross-attention path, but there’s no assertion that the old uncached pattern (attn(x, context=ctx, ...)) now fails. Please add one failure-mode test (e.g., assertRaisesRegex) so this contract change can’t silently regress.

Proposed test addition
+    `@pytest.mark.skipif`(not torch.cuda.is_available(), reason="CUDA not available")
+    def test_cross_attention_uncached_context_rejected(self):
+        """Uncached cross-attention must be rejected after invariant tightening."""
+        from tensorrt_llm._torch.visual_gen.models.ltx2.transformer_ltx2 import LTX2Attention
+
+        batch_size = 1
+        q_seq = 8
+        kv_seq = 4
+        query_dim = 4096
+        context_dim = 4096
+        heads = 32
+        head_dim = 128
+        dtype = torch.bfloat16
+
+        config = _create_config("VANILLA")
+        attn = (
+            LTX2Attention(
+                query_dim=query_dim,
+                context_dim=context_dim,
+                heads=heads,
+                dim_head=head_dim,
+                config=config,
+                layer_idx=0,
+            )
+            .to(self.DEVICE, dtype=dtype)
+            .eval()
+        )
+
+        x = torch.randn(batch_size, q_seq, query_dim, device=self.DEVICE, dtype=dtype) * 0.02
+        ctx = torch.randn(batch_size, kv_seq, context_dim, device=self.DEVICE, dtype=dtype) * 0.02
+
+        with self.assertRaisesRegex((AssertionError, ValueError), "self-attention|cross-attention|pre_projected_kv"):
+            _ = attn(x, context=ctx, pe=None)

Also, because this PR only touches unit tests under tests/unittest/, QA integration test-list updates under tests/integration/test_lists/qa/ are unnecessary here.

As per coding guidelines: “Coverage expectations: Assess whether new/changed tests cover happy path, important edge cases, and failure modes relevant to the feature or fix.”

Also applies to: 235-240

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@tests/unittest/_torch/visual_gen/test_ltx2_attention.py` around lines 193 -
199, The test suite adds a cached cross-attention path but misses a negative
test to ensure uncached cross-attention (calling attn(x, context=ctx, ...)) now
fails; add an assertion using assertRaisesRegex around calling attn(x,
context=ctx, pe=None) (or attn.forward) to confirm the new invariant is
enforced, e.g., call project_kv to get (k, v) and assert that calling attn with
context=ctx (uncached pattern) raises the expected error message; reference the
attn object, its project_kv method, and the forward/__call__ invocation to
locate where to insert the failure-mode test.
tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py (1)

312-348: 💤 Low value

Consider adding the same assertion to _forward_unfused for consistency.

The fused path (lines 285-289) asserts context is None when pre_projected_kv is None, but _forward_unfused lacks this check. While the docstring at lines 330-331 documents this contract ("uncached path applies pe to both Q and K (matches self-attn behavior)") and production never enters this path, adding the same assertion would make the invariant explicit and catch test/ablation misuse early.

🔧 Proposed fix for consistency
         if pre_projected_kv is not None:
             k, v = pre_projected_kv
             q = self.to_q(x)
             if self.qk_norm:
                 q = self.norm_q(q)
         else:
+            assert context is None, (
+                "uncached _forward_unfused is only valid for self-attn "
+                "(context=None); for cross-attn pass pre_projected_kv "
+                "from self.project_kv(context, pe=<k_rope>)."
+            )
             q, k, v = self.get_qkv(x, context)
             q, k = self.apply_qk_norm(q, k)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py` around lines
312 - 348, Add the same invariant check present in the fused path to
_forward_unfused: when pre_projected_kv is None assert that context is None to
make the uncached Q/K rotation contract explicit and fail fast; place this
assertion near the start of _forward_unfused (before calling self.get_qkv or any
Q/K processing) so that the function enforces the intended uncached-path
precondition.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py`:
- Around line 312-348: Add the same invariant check present in the fused path to
_forward_unfused: when pre_projected_kv is None assert that context is None to
make the uncached Q/K rotation contract explicit and fail fast; place this
assertion near the start of _forward_unfused (before calling self.get_qkv or any
Q/K processing) so that the function enforces the intended uncached-path
precondition.

In `@tests/unittest/_torch/visual_gen/test_ltx2_attention.py`:
- Around line 193-199: The test suite adds a cached cross-attention path but
misses a negative test to ensure uncached cross-attention (calling attn(x,
context=ctx, ...)) now fails; add an assertion using assertRaisesRegex around
calling attn(x, context=ctx, pe=None) (or attn.forward) to confirm the new
invariant is enforced, e.g., call project_kv to get (k, v) and assert that
calling attn with context=ctx (uncached pattern) raises the expected error
message; reference the attn object, its project_kv method, and the
forward/__call__ invocation to locate where to insert the failure-mode test.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: c8e8bb14-96ad-4328-a460-946e01203c00

📥 Commits

Reviewing files that changed from the base of the PR and between 526d7ee and feae178.

📒 Files selected for processing (2)
  • tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py
  • tests/unittest/_torch/visual_gen/test_ltx2_attention.py

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50298 [ run ] triggered by Bot. Commit: feae178 Link to invocation

@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch from feae178 to 7553ce1 Compare May 26, 2026 06:33
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch 2 times, most recently from 444d309 to 033fc8c Compare May 26, 2026 06:37
@luyiyun1021 luyiyun1021 changed the title [None][refactor] LTX-2 attention: drop dead k_pe parameter; restrict uncached SEPARATE_QKV to self-attn [TRTLLM-12963][refactor] LTX-2 attention: drop dead k_pe parameter May 26, 2026
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50301 [ run ] triggered by Bot. Commit: 033fc8c Link to invocation

@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50298 [ run ] completed with state ABORTED. Commit: feae178

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50303 [ run ] triggered by Bot. Commit: 033fc8c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50301 [ run ] completed with state ABORTED. Commit: 033fc8c

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50303 [ run ] completed with state SUCCESS. Commit: 033fc8c
/LLM/main/L0_MergeRequest_PR pipeline #39833 completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50331 [ run ] triggered by Bot. Commit: 033fc8c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #50331 [ run ] completed with state SUCCESS. Commit: 033fc8c
/LLM/main/L0_MergeRequest_PR pipeline #39858 completed with status: 'SUCCESS'

CI Report

Link to invocation

Comment thread tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py Outdated
Comment thread tensorrt_llm/_torch/visual_gen/models/ltx2/transformer_ltx2.py Outdated
@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch 2 times, most recently from 1c9b55e to 3575972 Compare May 29, 2026 03:11
@luyiyun1021 luyiyun1021 changed the title [TRTLLM-12963][refactor] LTX-2 attention: drop dead k_pe parameter [None][refactor] LTX-2 attention: drop dead k_pe parameter May 29, 2026
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch from 3575972 to b3b5e22 Compare May 29, 2026 03:52
@luyiyun1021 luyiyun1021 changed the title [None][refactor] LTX-2 attention: drop dead k_pe parameter [None][refactor] LTX-2 attention: drop dead k_pe parameter; require cached cross-attn May 29, 2026
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch from b3b5e22 to 462f662 Compare May 29, 2026 04:46
@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch from 462f662 to 094e249 Compare June 9, 2026 03:25
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #52932 [ run ] triggered by Bot. Commit: 094e249 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #52932 [ run ] completed with state SUCCESS. Commit: 094e249
/LLM/main/L0_MergeRequest_PR pipeline #42177 completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53082 [ run ] triggered by Bot. Commit: 094e249 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53082 [ run ] completed with state SUCCESS. Commit: 094e249
/LLM/main/L0_MergeRequest_PR pipeline #42294 completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch from 094e249 to 11e4be3 Compare June 9, 2026 16:14
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53097 [ run ] triggered by Bot. Commit: 11e4be3 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53097 [ run ] completed with state FAILURE. Commit: 11e4be3
/LLM/main/L0_MergeRequest_PR pipeline #42305 completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch from 11e4be3 to b0cdceb Compare June 10, 2026 04:05
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53224 [ run ] triggered by Bot. Commit: b0cdceb Link to invocation

@luyiyun1021
luyiyun1021 enabled auto-merge (squash) June 10, 2026 11:11
@luyiyun1021
luyiyun1021 disabled auto-merge June 10, 2026 11:12
@luyiyun1021 luyiyun1021 changed the title [None][refactor] LTX-2 attention: drop dead k_pe parameter; require cached cross-attn [TRTLLM-12963][refactor] LTX-2 attention: drop dead k_pe parameter; require cached cross-attn Jun 10, 2026
@luyiyun1021
luyiyun1021 enabled auto-merge (squash) June 10, 2026 11:12
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53224 [ run ] completed with state SUCCESS. Commit: b0cdceb
/LLM/main/L0_MergeRequest_PR pipeline #42418 completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

…ached cross-attn

k_pe was the optional per-K rope override on LTX2Attention.forward and _forward_unfused. It became dead code after the earlier norm+rope fusion work moved K-rope into project_kv. That move had two goals: (1) eliminate the cos/sin all-gather under Ulysses (rope is per-token element-wise and commutes with seq-dim concat, so rotating K on the local shard before all-gather is bit-identical and saves a collective); (2) enable K-norm + K-rope to go through a single fused kernel (fused_dit_split_norm_rope) inside project_kv. After that, every production cross-attn caller pre-rotates K via project_kv and calls forward with pre_projected_kv=(k, v) and k_pe=None.

Cleanup:

- Drop k_pe parameter from forward + _forward_unfused, drop k_pe=None kwargs from BasicAVTransformerBlock's a2v / v2a calls.

- Replace the k_pe-ternary 'k_pe if k_pe is not None else pe' in the uncached SEPARATE_QKV branch with just pe (it always was pe in practice; non-None k_pe was never wired).

- Enforce a clean cached-cross-attn invariant: cross-attn (context != None) requires pre_projected_kv. The uncached SEPARATE_QKV branch is now self-attn-only (context must be None; Q and K share pe by construction). Cross-attn through the uncached branch raises ValueError directing the caller to project_kv + pre_projected_kv (ValueError survives python -O). In LTX-2 production every cross-attn caller already uses the cached pattern, so this is a no-op there; it just kills a silent-mis-rotation footgun and the documented-but-unreachable inline fallback.

- Update BasicAVTransformerBlock.forward docstring (text_kv_video / text_kv_audio are required when their stream runs cross-attn, not 'falls back to inline computation').

- Update class + project_kv docstrings to drop k_pe references.

- Update TestLTX2CrossAttention unit tests to use the production cached pattern (project_kv → pre_projected_kv) instead of the now-rejected uncached cross-attn shape.

Tests: test_ltx2_attention.py (6/6) + test_ltx2_transformer.py (14/14) — 20/20 PASS. No production behavior change.
Signed-off-by: Yiyun Lu <55233584+luyiyun1021@users.noreply.github.com>
@luyiyun1021
luyiyun1021 force-pushed the dev/ltx2-remove-k-pe branch from b0cdceb to 6df8849 Compare June 10, 2026 15:56
@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53335 [ ] completed with state FAILURE. Commit: ``

Link to invocation

@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53471 [ run ] triggered by Bot. Commit: 6df8849 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53471 [ run ] completed with state SUCCESS. Commit: 6df8849
/LLM/main/L0_MergeRequest_PR pipeline #42634 completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

@luyiyun1021

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53766 [ run ] triggered by Bot. Commit: 6df8849 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53766 [ run ] completed with state SUCCESS. Commit: 6df8849
/LLM/main/L0_MergeRequest_PR pipeline #42886 completed with status: 'SUCCESS'

CI Report

Link to invocation

@luyiyun1021
luyiyun1021 merged commit f18d18d into NVIDIA:main Jun 12, 2026
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants