Skip to content

chore(deps): update loader dependencies major (major)#194

Open
dreadnode-renovate-bot[bot] wants to merge 1 commit into
mainfrom
renovate/major-loader-deps-major
Open

chore(deps): update loader dependencies major (major)#194
dreadnode-renovate-bot[bot] wants to merge 1 commit into
mainfrom
renovate/major-loader-deps-major

Conversation

@dreadnode-renovate-bot

@dreadnode-renovate-bot dreadnode-renovate-bot Bot commented Feb 24, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package Change Age Confidence
psutil ==6.1.1 → ==7.2.2 age confidence
transformers ==4.57.6 → ==5.14.0 age confidence

Warning

Some dependencies could not be looked up. Check the Dependency Dashboard for more information.

Release Notes

giampaolo/psutil (psutil)

v7.2.2

Compare Source

v7.2.1

Compare Source

v7.2.0

Compare Source

v7.1.3

Compare Source

v7.1.2

Compare Source

v7.1.1

Compare Source

v7.1.0

Compare Source

v7.0.0

Compare Source

huggingface/transformers (transformers)

v5.14.0

Compare Source

Release v5.14.0

New Model additions

Inkling (fresh from Thinking Machines): 975B total, 41B active
image

Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and
generates text outputs. It is intended for use in English and other languages, and across
multiple coding languages. The model is designed to be used by developers building AI-
powered applications, including agentic and tool-use systems, coding assistants, chatbots, and
retrieval-augmented generation systems, and is suitable for general-purpose conversational
use, instruction-following, and other natural language and multimodal tasks. It is released with
open weights to support research, fine-tuning and integration into third-party products by
downstream developers.

TIPSv2
image

Links: Documentation

TIPSv2 DPT
image

Links: Documentation

🚨 Breaking changes

GPTNeoX now remaps embed_out to lm_head and GPTBigCode has _supports_attention_backend = True enabled for vLLM compatibility; users relying on the previous weight naming or attention backend behavior for these models should update their code accordingly.

  • 🚨 Fix GPTBigCode and GPTNeoX for the Transformers modelling backend for vLLM (#​47198) by @​hmellor

Kernels

Several kernel-related fixes and improvements were made, including pinning the kernels dependency to a compatible version in the benchmark workflow, removing a deprecated package_name argument from LocalLayerRepository, and making the DeepGEMM Triton fallback more robust when CUDA_HOME is unset or misconfigured. Additionally, SDPA prefill was updated to leverage the FlashAttention kernel with StaticCache, yielding significant performance gains (up to 260% faster for large input sizes).

Generation

Generation improvements include adding Multi-Token Prediction (MTP) decoding support, static ensemble verification for speculative decoding to improve draft token acceptance rates, and a fix for crashes in greedy assisted generation with different tokenizers. A misleading double-negative warning message for synced_gpus in continuous batching mode was also corrected.

Performance

Fixed a Flash Attention performance regression affecting models like Qwen3-VL and resolved a MoE decode optimization bug where the grouped-to-batched matrix multiplication switch was not applied to experts residing in submodels (e.g., VLMs with a nested text config).

Cache

Cache dispatch logic was simplified by introducing explicit layer-type mappings for sliding and static layers, reducing complexity in cache routing. Additionally, fixes were made for read-only cache failures in CPU CI environments and for MPS graph cache growth during variable-length batch training on Apple Silicon.

Bugfixes and improvements

Significant community contributions

The following contributors have made significant changes to the library over the last release:

  • @​ArthurZucker
    • v5.14.0
  • @​tarekziade
    • ci: cover xet as well (runtime error) (#​47338)
    • Pin kernels to compatible version in benchmark workflow (#​47339)
    • Switch mlinter to 0.1.2 (#​47172)
    • Make executorch exporter tests always use xnnpack backend (#​47201)
    • Remove executorch from all-latest-gpu image + add torch smoke test (#​47196)
    • we want to run the CI in the release branches (#​47125)
  • @​remi-or
    • [Nit] Add kernels_fallback_ok kwarg to is_flash_attn_N_available (#​47318)
    • [Nit] Add expectations for gemma4 tests on H100 (#​47311)
    • [Fix] Remove deprecated argument from kernels call (#​47100)
    • [Fix] Make DeepGEMM triton fallback more robust (#​47126)
    • Fix experts implementation in two spots (#​47097)
    • [Fix] Remove old automatic cross attn pattern from output recorders (#​47117)
  • @​ydshieh
    • tests: reduce processor test memory usage by using tiny Hub checkpoints (#​47213)
    • Fix flash-attn Docker build broken by setuptools 83 removing pkg_resources (#​47251)
    • Fix InputTokensDetails missing cache_write_tokens for openai>=2.34.0 (#​47248)
    • Revert "Trigger a scheduled run" (#​47249)
    • Fix CI read-only cache failures by patching cached_files in conftest (#​47043)
    • Trigger a scheduled run (#​47209)
    • tests: reduce processor test memory usage and use tiny test assets (#​47168)
    • processor tests: use tiny Hub repos to reduce CI memory (#​47115)
  • @​eladsegal
    • Add heterogeneous config support (per-layer configuration) (#​45333)
  • @​eustlb
  • @​Ternura143

v5.13.1: Patch release v5.13.1

Compare Source

Patch release v5.13.1

This patch is focused on enabling transformers for the latest release of vllm!

v5.13.0

Compare Source

Release v5.13.0

New Model additions

KimiK 2.5, 2.6, and 2.7
image

This release includes the architecture for Kimi 2.5 which is used by 2.5-2.7:

Kimi K2.5 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration. The model was proposed in Kimi K2.5: Visual Agentic Intelligence and further improved in [Kimi K2.6: Advancing Open-Source Coding](Kimi K2.5: Visual Agentic Intelligence).

Kimi K2.5 achieves significant improvements on complex, end-to-end coding tasks, generalizing robustly across programming languages (Rust, Go, Python) and domains spanning front-end, DevOps, and performance optimization. The model is capable of transforming simple prompts and visual inputs into production-ready interfaces and lightweight full-stack workflows, generating structured layouts, interactive elements, and rich animations with deliberate aesthetic precision.

Links: Documentation

MiMo-V2-Flash
image

MiMo-V2-Flash is a Mixture-of-Experts (MoE) language model developed by the Xiaomi MiMo team. Designed to establish a new balance between long-context modeling capabilities and inference efficiency, the model is built for strong performance in complex reasoning and agentic tasks. Trained on 27T tokens with native 32k sequence lengths, MiMo-V2-Flash seamlessly supports an extended 256K context window while significantly reducing KV-cache storage compared to standard global attention models.

Links: Documentation

Nemotron 3.5 ASR
image

Nemotron 3.5 ASR is a 600M-parameter multilingual speech recognition model from NVIDIA, built for high-quality transcription in both low-latency streaming and high-throughput batch settings, with native punctuation and capitalization. For streaming, it offers configurable chunk sizes—80ms, 160ms, 560ms, and 1120ms, letting users trade off latency against accuracy to suit their application. Its cache-aware FastConformer-RNNT architecture is central to this capability: unlike traditional buffered streaming, which repeatedly reprocesses overlapping audio windows, the model processes only each new incoming chunk while reusing cached encoder context from prior chunks. This eliminates redundant computation, significantly improves efficiency, and minimizes end-to-end delay without sacrificing accuracy, making it well suited to real-time transcription workloads.

Links: Documentation

NemotronAsrStreaming

Nemotron ASR Streaming is a 600M-parameter English speech recognition model from NVIDIA, built for high-quality transcription in both low-latency streaming and high-throughput batch settings, with native punctuation and capitalization. For streaming, it offers configurable chunk sizes—80ms, 160ms, 560ms, and 1120ms, letting users trade off latency against accuracy to suit their application. Its cache-aware FastConformer-RNNT architecture is central to this capability: unlike traditional buffered streaming, which repeatedly reprocesses overlapping audio windows, the model processes only each new incoming chunk while reusing cached encoder context from prior chunks. This eliminates redundant computation, significantly improves efficiency, and minimizes end-to-end delay without sacrificing accuracy, making it well suited to real-time transcription workloads.

Links: Documentation

Qwen3 ASR
image

Qwen3 ASR is an automatic speech recognition model from Alibaba's Qwen team that combines a Whisper-style audio encoder with a Qwen3 language model decoder for speech-to-text transcription. The model supports automatic language detection and multilingual transcription.

A forced aligner model is also included. It can be used to timestamp a provided transcript and its audio. It uses the same audio encoder model with a classification head that predicts a word's length. This model can be used with the transcript from any ASR model (see the example below with Parakeet CTC).

Links: Documentation

ZAYA
image

ZAYA1 is a 760M active / 8.4B total parameter MoE language model trained by Zyphra. It combines Compressed
Convolutional Attention (CCA), a nonlinear ZAYA1 router, and residual scaling.

Links: Documentation

VideoPrism

The VideoPrism model was proposed in the paper VideoPrism: A Foundational Visual Encoder for Video Understanding by Google DeepMind (blog post).

VideoPrism is a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. The model is pretrained on a large-scale heterogeneous corpus containing 36M high-quality video-caption pairs and 582M video clips with noisy parallel text (e.g., ASR transcripts). The pretraining approach improves upon masked autoencoding through global-local distillation of semantic video embeddings and a token shuffling scheme, enabling the model to focus primarily on the video modality while leveraging text associated with videos. VideoPrism achieves state-of-the-art performance on 31 out of 33 video understanding benchmarks across four broad task groups, from web video question answering to computer vision for science.

Links: Documentation

RADIO

RADIO (Reduce All Domains Into One) is a family of vision foundation models from NVIDIA trained by multi-teacher distillation (e.g. CLIP, DINOv2, SAM) into a single ViT backbone. It produces both an image-level summary embedding and dense spatial features, and supports variable input resolutions through a Cropped Position Embedding (CPE) patch generator.

Links: Documentation

MiniCPM3

MiniCPM3 is the third-generation MiniCPM dense language model from OpenBMB. The 4B variant
(openbmb/MiniCPM3-4B) outperforms many 7B–9B open
models on standard benchmarks while remaining lightweight enough for on-device usage.

MiniCPM3 combines several architectural ideas:

  • Multi-head Latent Attention (MLA) from DeepSeek-V2, which compresses the key/value cache
    into a low-rank latent representation while still using rotary embeddings on a portion of the
    query/key heads.
  • A standard SwiGLU MLP (no MoE).
  • Three scalar scaling factors that govern signal flow:
    • scale_emb — scales input embeddings.
    • scale_depth / sqrt(num_hidden_layers) — scales residual connections.
    • hidden_size / dim_model_base — scales hidden states before the language model head.

Links: Documentation

Breaking changes

A broad set of modeling changes have been made to standardize layer declarations, mask/cache construction, and hybrid-attention handling, making many models cleanly exportable (ONNX, torch.export, ExecuTorch) and fullgraph-compilable — users relying on internal modeling APIs may need to update their code accordingly.

Attention masking for image tokens in Gemma 3/4 models has been fixed to correctly respect sliding window boundaries in local layers, which changes model behavior and may affect reproducibility of previous results.

The Expert Parallelism (EP) router contract has been corrected across many models and FP8 scale format handling has been fixed, requiring users of EP or FP8 quantization with affected models to verify their configurations and potentially update conversion mappings.

The Kernels integration has been synced to the latest version, which includes a breaking change where model-type repositories are no longer accepted by the kernels interface — users must migrate to the updated kernel repository format as shown in the updated tests.

HfExporters: Native, Unified export for PyTorch / ONNX / ExecuTorch

thumbnail

A native, in-Transformers export pipeline — one base class (HfExporter), three subclasses for the runtimes we care about, one unified API:

Exporter Output Runtime
DynamoExporter ExportedProgram Any PyTorch runtime, AOT compilation
OnnxExporter ONNXProgram Any ONNX runtime (ORT, TensorRT, OpenVINO, …)
ExecutorchExporter ExecutorchProgramManager Mobile and edge (ExecuTorch)

Same call shape across all three. Dynamic shapes by default. Generation-style models split automatically into prefill + decode (+ vision/audio sub-encoders for VLMs).

from transformers import AutoModelForMaskedLM, AutoTokenizer
from transformers.exporters import OnnxExporter, OnnxConfig

model_id = "hf-internal-testing/tiny-random-BertForMaskedLM"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForMaskedLM.from_pretrained(model_id).eval()
inputs = tokenizer(["Hello, my dog is cute"] * 2, return_tensors="pt")
onnx_program = OnnxExporter().export(model, inputs, config=OnnxConfig(dynamic=True))

new_input = tokenizer("Hello, my cat is so adorable!", return_tensors="pt")
torch.testing.assert_close(
    onnx_program.call_reference(**new_input)[0],   # numpy reference
    onnx_program(**new_input)[0],                  # onnxruntime
    rtol=1e-4, atol=1e-4,
)

Swap one line for another runtime — DynamoExporter() / DynamoConfig or ExecutorchExporter() / ExecutorchConfig(backend=...).

For generative models the prefill/decode split is captured automatically:

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.exporters import OnnxExporter, OnnxConfig

model_id = "hf-internal-testing/tiny-random-LlamaForCausalLM"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).eval()
inputs = tokenizer(["Hello, my dog is cute"] * 2, return_tensors="pt")

artifacts = OnnxExporter().export_for_generation(model, inputs, config=OnnxConfig(dynamic=True))

# {"prefill": ONNXProgram, "decode": ONNXProgram}
# For VLMs: also vision_encoder, audio_encoder, multi_modal_projector, language_model, lm_head

Kernels

Kernels: Fixed a silent SDPA math-kernel fallback for GQA models with head_dim > 256 (e.g., Gemma4) that caused O(S²) memory materialization, and resolved a regression where use_kernels=True failed to apply kernel mappings. Additional improvements include lazy loading of the default kernel mapping to prevent import failures with incompatible kernel versions, ROCm routing to AITER Triton kernels for AMD GPUs, GB10/SM121 Hub-kernel support for Qwen3.6 Gated DeltaNet, and expanded documentation for the kernel API.

✂ Note

PR body was truncated to here.

Configuration

📅 Schedule: (UTC)

  • Branch creation
    • At any time (no schedule defined)
  • Automerge
    • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

  • If you want to rebase/retry this PR, check this box

This PR has been generated by Mend Renovate.

@dreadnode-renovate-bot dreadnode-renovate-bot Bot added the type/digest Dependency digest updates label Feb 24, 2026
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch 3 times, most recently from 07525d6 to 3ac3e72 Compare March 1, 2026 00:53
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from 3ac3e72 to 4daa5d1 Compare March 8, 2026 00:48
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch 2 times, most recently from 3e0d62f to 4b95150 Compare April 1, 2026 00:57
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from 4b95150 to 40a28f1 Compare April 8, 2026 00:52
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch 2 times, most recently from 85f7052 to c4f4579 Compare April 19, 2026 00:59
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from c4f4579 to 37b26b9 Compare April 26, 2026 01:01
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from 37b26b9 to ca4e25e Compare May 3, 2026 01:07
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from ca4e25e to b5496fe Compare May 10, 2026 01:09
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from b5496fe to a845574 Compare May 17, 2026 01:11
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from a845574 to f7682ea Compare May 24, 2026 01:12
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from f7682ea to cfc6d09 Compare June 7, 2026 01:19
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch 2 times, most recently from e691441 to 27d20a0 Compare June 17, 2026 01:21
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from 27d20a0 to 2fe9194 Compare June 28, 2026 01:16
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch 2 times, most recently from 0a2bdbe to 630f8a7 Compare July 15, 2026 00:44
@dreadnode-renovate-bot
chore(deps): update loader dependencies major
482234c 
| datasource | package      | from   | to     |
| ---------- | ------------ | ------ | ------ |
| pypi       | psutil       | 6.1.1  | 7.2.2  |
| pypi       | transformers | 4.57.6 | 5.14.0 |
@dreadnode-renovate-bot
dreadnode-renovate-bot Bot force-pushed the renovate/major-loader-deps-major branch from 630f8a7 to 482234c Compare July 19, 2026 00:54
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

type/digest Dependency digest updates

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

0 participants