btw
btw is turning into an agentic R harness that no longer needs you to be in R
Comparison · ai-assistants
ONNX Runtime vs safetensors
A side-by-side editorial comparison of ONNX Runtime and safetensors — release velocity, themes, recent moves, and the top alternatives to consider.
ONNX Runtime vs safetensors: at a glance
What is ONNX Runtime?
ONNX Runtime is retiring WebGL for WebGPU and turning on telemetry outside Windows.
v1.29.0 announces the deprecation of WebGL and JSEP in onnxruntime-web, naming the native WebGPU execution provider as the path forward, and adds POSIX telemetry on Linux, macOS, Android and iOS for telemetry-enabled builds, disabled via ORT_DISABLE_TELEMETRY. It also carries a long list of security fixes — a TensorRT path-traversal vulnerability, plus rank, shape and bounds validation across a dozen kernels. Separately, the WebGPU plug-in reached v0.2.1 with fused FlashAttention decode kernels for any sequence length and Qwen3 and Gemma 4 model paths, while v1.28.0 made cuDNN and cuFFT optional at runtime to shrink the CUDA redistributable.
What is safetensors?
safetensors for R changes hands with no code change to show for it.
The R safetensors package reads and writes the safetensors tensor format for the torch stack. The single release in view is administrative: maintainership passes to Tomasz Kalinowski. No functional change is recorded.
ONNX Runtime vs safetensors: editorial side-by-side
ONNX Runtime
6.3AI-ASSISTANTS
ONNX Runtime is retiring WebGL for WebGPU and turning on telemetry outside Windows.
◆ Current state
v1.29.0 announces the deprecation of WebGL and JSEP in onnxruntime-web, naming the native WebGPU execution provider as the path forward, and adds POSIX telemetry on Linux, macOS, Android and iOS for telemetry-enabled builds, disabled via ORT_DISABLE_TELEMETRY. It also carries a long list of security fixes — a TensorRT path-traversal vulnerability, plus rank, shape and bounds validation across a dozen kernels. Separately, the WebGPU plug-in reached v0.2.1 with fused FlashAttention decode kernels for any sequence length and Qwen3 and Gemma 4 model paths, while v1.28.0 made cuDNN and cuFFT optional at runtime to shrink the CUDA redistributable.
◆ Where it's heading
The browser story is consolidating onto one backend after years of maintaining three, and the WebGPU plug-in's independent release track is what made that credible — the attention work landed there first. On the core runtime the direction is subtraction: fewer linked CUDA libraries, removed TensorRT fused kernels, a deprecated CUDA 12, and a steady stream of input-validation hardening that suggests sustained security review. Note the feed is non-monotonic, with v1.26.0 and v1.29.0 published minutes apart.
◆ Prediction
CUDA 12 removal in 1.27.0 was already announced, and the CUDA runtime is slated to move into a dedicated execution provider — that separation is the next structural change to watch.
safetensors
0.0AI-ASSISTANTS
safetensors for R changes hands with no code change to show for it.
◆ Current state
The R safetensors package reads and writes the safetensors tensor format for the torch stack. The single release in view is administrative: maintainership passes to Tomasz Kalinowski. No functional change is recorded.
◆ Where it's heading
With only a maintainer line to go on, the package reads as stable and low-churn. The same handover lands in tfevents two minutes later and in torchdatasets days after, so this is part of a consolidation of mlverse maintainership rather than anything specific to safetensors.
◆ Prediction
The entries do not support a confident prediction about features; the most likely next release is another housekeeping bump tied to the wider mlverse handover.
Alternatives to ONNX Runtime and safetensors
Other ai-assistants products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either ONNX Runtime or safetensors.
ellmer
ellmer stopped being a chat wrapper and started shipping the parts production LLM code needs
tfevents
tfevents logs TensorBoard events from R, and this release only changes who maintains it.
torchdatasets
torchdatasets ships custodial work as mlverse gathers its torch satellites under one maintainer.
mlr3tuningspaces
A curated catalogue of published hyperparameter search spaces, now reaching deep neural networks
mlr3hyperband
Hyperband tuning for mlr3, now built on an asynchronous backend it treats as mandatory
See all ONNX Runtime alternatives → · See all safetensors alternatives →
Recent activity from ONNX Runtime and safetensors
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 3d agoONNX RuntimeONNX Runtime 1.29 deprecates WebGL and JSEP, adds POSIX telemetry ⚡
- 3d agoONNX RuntimeONNX Runtime 1.26 adds RISC-V vector support and .ort memory mapping
- 16d agoONNX RuntimeWebGPU plug-in: FlashAttention fusions, Qwen3 and Gemma 4 paths
- 21d agoONNX RuntimeONNX 1.22 upgrade, slimmer CUDA footprint, experimental C API
- 1mo agoONNX RuntimePatch release: QMoE batch-1 decode fast path and fixes
- 1mo agoONNX RuntimeSecurity-hardening minor targeting ONNX 1.21
- 3mo agosafetensorsMaintainership passes to Tomasz Kalinowski
Frequently asked questions
What is the difference between ONNX Runtime and safetensors?
They serve adjacent needs but don't currently overlap on shipped themes. ONNX Runtime is currently shipping more aggressively (velocity 6.3 vs 0.0), with 1 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is ONNX Runtime better than safetensors?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. ONNX Runtime is currently shipping more aggressively (velocity 6.3 vs 0.0), with 1 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other ai-assistants products to evaluate alongside.
What are the best alternatives to ONNX Runtime?
Top ONNX Runtime alternatives in ai-assistants are ranked by recent ship velocity. Browse the "ONNX Runtime alternatives" section above for the current picks, or visit /alternatives/onnx-runtime for the full list with editorial commentary on each.
What are the best alternatives to safetensors?
Top safetensors alternatives in ai-assistants are ranked by recent ship velocity. Browse the "safetensors alternatives" section above for the current picks, or visit /alternatives/safetensors-r for the full list with editorial commentary on each.