Bump onnx from 1.12.0 to 1.13.0 by dependabot[bot] · Pull Request #1 · NVIDIA/TensorRT-LLM

dependabot · 2023-09-20T07:34:02Z

Bumps onnx from 1.12.0 to 1.13.0.

Release notes

v1.13.0

ONNX v1.13.0 is now available with exciting new features! We would like to thank everyone who contributed to this release! Please visit onnx.ai to learn more about ONNX and associated projects.

New operators

Col2Im added in #3948

BitwiseNot added in #4497

BitwiseAnd, BitwiseOr and BitwiseXor added in #4496

Operator extensions

Resize - New attributes: antialias, axes and keep_aspect_ratio_policy, allow for both scales and sizes to be provided when one of them is an empty constant #4126, #4388

Pad - New attribute axes #4190

OptionalHasElement - New input types handling #4326

OptionalHasElement and OptionalGetElement - Accept tensor and sequence types #4421

ScatterElement and ScatterND - Add max and min as supported reduction attributes #4411

Split - Add support for uneven tensor splitting and a new num_outputs attribute #4481

LpPool - New attributes: ceil_mode and dilations #4534

Function updates

CenterCropPad added in #4190

mish added in #4350

GroupNormalization added in #4621

Reference Python runtime

Reference Python runtime dependent on only Python and numpy has been added. #4483

Python 3.11 support

ONNX 1.13.0 supports Python 3.11. #4490

Apple Silicon support

Support for M1/M2 ARM processors has been added. #4642

More

ONNX 1.13.0 also comes with numerous:

bugfixes

infrastructure improvements

CI improvements

documentation updates

security updates

For full details see Logistics for ONNX Release 1.13.0.

Deprecation notice

TENSOR_TYPE_TO_STORAGE_TENSOR_TYPE has been deprecated #4270

ONNXIFI: ONNX Interface for Framework Integration has been deprecated #4431

Installation

You can upgrade to the latest release using pip install onnx --upgrade or build from source following the README instructions.

Contributors

Thanks to these individuals for their contributions in this release since last 1.12.0 release: @AnandKri, @cbourjau, @jcwchen, @gramalingam, @garymm, @GaetanLepage, @ilya-lavrenov, @jnovikov, @JackBoosY, @jbachurski, @tjich, @jantonguirao, @justinchuby, @natke, @philass, @prasanthpul, @p-wysocki, @SpaceIm, @stephenneuendorffer,@take-cheeze, @sechkova, @thiagocrepaldi, @xadupre, @mszhanyi, @yuanyao-nv, @andife, @daquexian, @kylesayrs, @liqunfu, @longlee0622, @HSQ79815, @williamberman, @YanBC

... (truncated)

Changelog

Sourced from onnx's changelog.

Operator Changelog

This file is automatically generated from the def files via this script. Do not modify directly and instead edit operator definitions.

For an operator input/output's differentiability, it can be differentiable, non-differentiable, or undefined. If a variable's differentiability is not specified, that variable has undefined differentiability.

ai.onnx (default)

Version 1 of the default ONNX operator set

Abs-1

Absolute takes one input data (Tensor) and produces one output data (Tensor) where the absolute is, y = abs(x), is applied to the tensor elementwise.

Version

This version of the operator has been available since version 1 of the default ONNX operator set.

Attributes

Inputs

Outputs

Type Constraints

... (truncated)

Commits

1ba7856 Mark final RC (#4696)
7adb421 misc fixes for issues found in ort integration (#4681) (#4695)
a913015 Mark release as rc1 (#4674)
3fd41d2 Bump version (#4666)
bad0697 Add LpPool-18 - add ceil_mode and dilations attributes (#4534)
7a1fae4 make primary ops function step 2 (#4512)
8fb26ed Fixed some typos in python.rst (#4668)
9955f35 Fix typo in python.rst (#4667)
cd6e5db Consider GraphInferenceContext in inference functions: InferenceContext (#4632)
466edb7 Add Python 3.11 support (#4490)
Additional commits viewable in compare view

You can trigger a rebase of this PR by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR
@dependabot recreate will recreate this PR, overwriting any edits that have been made to it
@dependabot merge will merge this PR after your CI passes on it
@dependabot squash and merge will squash and merge this PR after your CI passes on it
@dependabot cancel merge will cancel a previously requested merge and block automerging
@dependabot reopen will reopen this PR if it is closed
@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
@dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the Security Alerts page.

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.

Bumps [onnx](https://github.com/onnx/onnx) from 1.12.0 to 1.13.0. - [Release notes](https://github.com/onnx/onnx/releases) - [Changelog](https://github.com/onnx/onnx/blob/main/docs/Changelog.md) - [Commits](onnx/onnx@v1.12.0...v1.13.0) --- updated-dependencies: - dependency-name: onnx dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com>

dependabot · 2023-12-26T12:38:44Z

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.

* Add README * Add unified converter (#1) * init v3 lite feat * fix moe topk method * fix noaux_tc logic * fix deepseek v3 normal rope * refactor * wo conversion ok debugging build * add quantize for attn.dense * add unified converter support * testing unified converter * add convert checkpoint and update docs --------- Co-authored-by: Zeyu Wang <zeyuw@nvidia.com> * update README * add FP8 notes * Update run.py result * Update V3 README * Update usages of FP8 to BF16 instruction * fix model name mapping (#2) * Update HF ckpt BF16 conversion. * fix config of deepseek kv cache * Remove source code * Deepseek V3 FP8 Support --------- Co-authored-by: jershi425 <83951930+jershi425@users.noreply.github.com> Co-authored-by: Zeyu Wang <zeyuw@nvidia.com> Co-authored-by: Hanyue He <hanyueh@nvidia.com> Co-authored-by: root <root@h20-2.cm.cluster>

Improve bmm.

…ug fix (NVIDIA#1) Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * feat: ut for mooncake Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: add mooncake backend for cacheTransceiverTest Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: remove link Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * feat: add missing build Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * feat: add missing link Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: transferAgentTest Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: transferAgentTest Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: transferAgentTest Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: transferAgentTest Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: add status->wait Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * feat: add mooncake option for cacheTransceiver Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: rollbakc add status->wait Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * test: add debug msg Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: set batchId to invalid after xfer complete Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: set batchId to invalid after xfer complete Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: set batchId to invalid after xfer complete Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: set batchId to invalid after xfer complete Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * fix: add status->wait Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * refactor: simplify err msg Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> * refactor: isCompleted always return true after batchID freed Signed-off-by: wjueyao <wyao123@terpmail.umd.edu> --------- Signed-off-by: wjueyao <wyao123@terpmail.umd.edu>

Signed-off-by: Ludwig Schneider <lschneider@nvidia.com>

- Revert utils.py docstring changes (NVIDIA#1) - Remove disable_deep_gemm flag, use module-level quant_config=None (NVIDIA#2) - Replace Flux2SwiGLU with shared swiglu from _torch/modules (NVIDIA#3) - Unify Flux2PosEmbed into FluxPosEmbed with parameterized axes_dim (NVIDIA#4) - Replace Flux2FeedForward with shared GatedMLP (NVIDIA#6) - Revert pipeline.py post_load_weights; add create_weights() in FLUX transformer __init__ to match WAN's __post_init__ pattern (NVIDIA#7) - Refactor _get_quant_algo_for_layer to encapsulate hasattr logic (NVIDIA#9) - Remove partial docstrings that just repeat class names (NVIDIA#10) - Simplify bias flags to direct booleans (NVIDIA#11) - Unify apply_rotary_emb: delete FLUX copy, FluxPosEmbed outputs [1,S,1,D] matching WAN format so shared function unchanged (NVIDIA#12) - Remove dynamic=True from maybe_compile (NVIDIA#13) - Add @torch.compiler.disable on FluxPosEmbed.forward - Tighten FLUX.2 PSNR test threshold from 12 to 20 dB Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Kanghwan Jang <861393+karljang@users.noreply.github.com>

The ~21s MPI worker spawn overhead (Python imports, CUDA context, NCCL setup) runs concurrently with the server's model download. In S1, the 63.5s download fully hides this cost; in S2/S3, it becomes visible. Key updates: - "Reading the Results Tables": show separate S1/S2 timeline diagrams explaining the concurrency effect - Part 2 table: add "Worker spawn overhead" row (hidden/~21s) - S2>S1 explanation: split into real I/O difference + hidden parallelism - Insight #1: incorporate hidden parallelism finding - Insight #2: decompose ~25s "executor overhead" into ~21s worker spawn + ~4s other; identify two irreducible floors (spawn + warmup) Signed-off-by: Chien-Chun Hung <2679986+chienchunhung@users.noreply.github.com>

The S2>S1 result reflects the specific test environment (fast internal HF mirror at ~2 GB/s, 8 concurrent NFS readers, worst-case cold NFS). Public HF downloads would likely reverse the ordering. Updated both the Part 2 explanation and Analysis insight #1 to frame this as an observation about the benchmark environment rather than a general claim about NFS vs CDN performance. Signed-off-by: Chien-Chun Hung <2679986+chienchunhung@users.noreply.github.com>

…ta flow - S2 (NFS cold) is the realistic production cold-start scenario; S1's faster result is an artifact of a fast internal HF mirror - Added "Weight Loading Data Flow (TP=8)" section explaining the cooperative prefetch → full load → shard pattern and why every rank must load all safetensors files (HF shards by layer groups, TP shards by tensor slicing) - Highlighted the 8x redundant CPU memory inefficiency that MX addresses by streaming only the relevant shard to each rank - Updated Analysis insight #1 and MX+GMS impact projection to reflect production-centric framing Signed-off-by: Chien-Chun Hung <2679986+chienchunhung@users.noreply.github.com>

The download in S1 inherently warms the OS page cache (Linux retains written pages via write-back caching), so workers always hit warm page cache after a download — regardless of tmpfs vs local disk. This explains why S1 prefetch (3.5s) ≈ S3 prefetch (3.4s). S2 is slower because no prior operation warms the cache — workers read directly from cold NFS (65-99s). Rewrote "Why S2 > S1" explanation, Analysis insight #1, Storage Tier Matrix, and Part 1 description to center on this page-cache-warming mechanism. Signed-off-by: Chien-Chun Hung <2679986+chienchunhung@users.noreply.github.com>

Three issues fixed: 1. past_key_value (singular) renamed to past_key_values (plural) for LlamaAttention and GPT2Attention in transformers 5.x. 2. use_cache parameter removed from attention forward calls in transformers 5.x (cache is always updated in-place). 3. rope_theta/rope_scaling config attributes replaced with unified rope_parameters dict (same fix as test_gpt_attention.py). Without fix NVIDIA#1-2, the DynamicCache was never populated because the kwarg was silently ignored, causing an empty tuple from dynamic_cache_to_legacy and an IndexError at line 1026. Signed-off-by: Jonas Li <6110159+longlee0622@users.noreply.github.com>

brnguyen2 · 2026-08-18T19:14:22Z

/bot run

brnguyen2 · 2026-08-18T19:16:15Z

/bot run

brnguyen2 · 2026-08-18T19:16:58Z

/bot run

brnguyen2 · 2026-08-18T19:57:33Z

/bot run

brnguyen2 · 2026-08-18T19:58:16Z

/bot run

brnguyen2 · 2026-08-18T20:04:37Z

/bot run

brnguyen2 · 2026-08-19T14:16:50Z

/bot run

brnguyen2 · 2026-08-19T15:03:28Z

/bot run

brnguyen2 · 2026-08-21T12:14:04Z

/bot run

brnguyen2 · 2026-08-21T12:14:39Z

/bot run

brnguyen2 · 2026-08-21T12:14:49Z

/bot run

brnguyen2 · 2026-08-21T12:15:16Z

/bot run

brnguyen2 · 2026-08-21T13:32:14Z

/bot run

brnguyen2 · 2026-08-21T13:33:50Z

/bot run

brnguyen2 · 2026-08-21T13:34:37Z

/bot run

brnguyen2 · 2026-08-21T13:42:03Z

/bot run

brnguyen2 · 2026-08-21T13:42:24Z

/bot run

brnguyen2 · 2026-08-21T18:34:42Z

/bot run

brnguyen2 · 2026-08-31T15:53:18Z

/bot run

brnguyen2 · 2026-08-31T15:54:23Z

/bot run

brnguyen2 · 2026-08-31T16:22:01Z

/bot run

brnguyen2 · 2026-08-31T16:26:07Z

/bot run

brnguyen2 · 2026-08-31T18:50:35Z

/bot run

brnguyen2 · 2026-08-31T18:51:44Z

/bot run

brnguyen2 · 2026-08-31T19:45:06Z

/bot run

brnguyen2 · 2026-08-31T20:34:57Z

/bot run

brnguyen2 · 2026-08-31T20:37:40Z

/bot run

dependabot Bot added the dependencies Pull requests that update a dependency file label Sep 20, 2023

Shixiaowei02 closed this Dec 26, 2023

Shixiaowei02 deleted the dependabot/pip/onnx-1.13.0 branch December 26, 2023 12:38

zxs789 mentioned this pull request Jun 4, 2024

H20 Using random weights to infer llama2-13B results in a divide-by-zero error. #1717

Closed

4 tasks

netanel-haber mentioned this pull request Mar 24, 2025

Support Cohere Command-A (Cohere2ForCausalLM arch) #2912

Closed

Shang-Pin mentioned this pull request May 28, 2025

DeepSeek-R1-FP4 crashes when MTP is enabled #4708

Closed

4 tasks

climby mentioned this pull request Jun 10, 2025

Does TensorRT-LLM support DeepSeek-R1-671B-fp8 with B200 GPU ？ #5064

Closed

4 tasks

yuxianq referenced this pull request in yuxianq/TensorRT-LLM Jul 16, 2025

Merge pull request #1 from yuxianq/user/yuxianq/debug_moe

59ea58b

Improve bmm.

pythonjavaerlang mentioned this pull request Oct 15, 2025

[Feature]: support for nvidia/Qwen2.5-VL-7B-Instruct-FP4 #8404

Closed

1 task

nv-lschneider referenced this pull request in nv-lschneider/TensorRT-LLM Dec 1, 2025

Reviewing feedback #1

4b2a166

Signed-off-by: Ludwig Schneider <lschneider@nvidia.com>

harrisonlimh mentioned this pull request Jan 13, 2026

[Bug]: Empty output issue from invalid channel establishment after parsing, for gpt-oss-120b. Often caused by garbage, repeated output tokens. #10614

Closed

5 tasks

justremotephone mentioned this pull request Feb 5, 2026

[Bug]: Random "CUDA error: an illegal instruction was encountered" for gpt-oss 120B at Nvidia Spark. #11313

Closed

5 tasks

greg-kwasniewski1 mentioned this pull request Feb 21, 2026

[TRTLLM-11614][feat] Fixing multigpu tests #11615

Merged

1 task

kaiyux mentioned this pull request Mar 9, 2026

[TRTLLM-10421][perf] Add fused cat+fp8_quantize CUDA kernel for DSA indexer #11899

Merged

3 tasks

thorjohnsen mentioned this pull request Mar 16, 2026

[TRTLLM-11513][fix] eliminate dangling reference and TOCTOU races in KVCacheManager #12251

Closed

3 tasks

bmarimuthu-nv mentioned this pull request Mar 18, 2026

[#12289][feat] AutoDeploy Model Onboarding Sprint 03/19 - Part 1 #12209

Open

1 task

chuangz0 mentioned this pull request Mar 30, 2026

[TRTLLM-9526][feat] optimize host perf for python cache transceiver #12273

Merged

1 task

JunyiXu-nv mentioned this pull request Aug 27, 2026

[TRTLLM-12670][feat] add /start_profile and /stop_profile endpoints to trtllm… #13872

Open

1 task

kaiyux mentioned this pull request Aug 31, 2026

[None][feat] Add perf-analyze and perf-optimize skills to agent-flow #18434

Merged

1 task

longcheng-nv mentioned this pull request Aug 31, 2026

[None][feat] GVR V2 decode top-k goes hint-free by default: the bracket comes from the current row #18410

Merged

Uh oh!

Conversation

dependabot Bot commented on behalf of github Sep 20, 2023 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

v1.13.0

New operators

Operator extensions

Function updates

Reference Python runtime

Python 3.11 support

Apple Silicon support

More

Deprecation notice

Installation

Contributors

Operator Changelog

ai.onnx (default)

Version 1 of the default ONNX operator set

Abs-1

Version

Attributes

Inputs

Outputs

Type Constraints

Uh oh!

dependabot Bot commented on behalf of github Dec 26, 2023

Uh oh!

brnguyen2 commented Aug 18, 2026

Uh oh!

brnguyen2 commented Aug 18, 2026

Uh oh!

brnguyen2 commented Aug 18, 2026

Uh oh!

brnguyen2 commented Aug 18, 2026

Uh oh!

brnguyen2 commented Aug 18, 2026

Uh oh!

brnguyen2 commented Aug 18, 2026

Uh oh!

brnguyen2 commented Aug 19, 2026

Uh oh!

brnguyen2 commented Aug 19, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 21, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

Uh oh!

brnguyen2 commented Aug 31, 2026

dependabot Bot commented on behalf of github Sep 20, 2023 •

edited

Loading