Download Latest Version ONNX Runtime WebGPU Plugin EP v0.2.1 source code.zip (292.6 MB)
Email in envelope

Get an email when there's a new version of ONNX Runtime

Home / plugin-ep-webgpu_v0.2.1
Name Modified Size InfoDownloads / Week
Parent folder
ONNX Runtime WebGPU Plugin EP v0.2.1 source code.tar.gz 2026-07-28 285.9 MB
2 2 weekly downloads
ONNX Runtime WebGPU Plugin EP v0.2.1 source code.zip 2026-07-28 292.6 MB
24 24 weekly downloads
README.md 2026-07-28 3.7 kB
0
Totals: 3 Items   578.6 MB 26

Highlights

  • Major performance work for attention-heavy LLMs.
  • FlashAttention decode kernels were fused and extended for any sequence length (#28389).
  • FlashAttention prefill shared-memory path was generalized (#28520).
  • Dynamic max_k_step was enabled for NVIDIA (#28511).
  • QKV bias support was added for FlashAttention in MultiHeadAttention (#28380).

  • M4 Max-specific FlashAttention optimization landed (#27780).

  • Qwen3 and Gemma 4 model-path improvements.

  • QKV and MLP fusions for Qwen3-style models (#28280).
  • Q/K RMSNorm fusion into GroupQueryAttention for Qwen3-style models (#28484).
  • Opset 24 and KV-shared decoder layer support for Gemma 4 (#28501).

  • GroupQueryAttention now supports optional present-key/value outputs (#28242).

  • LinearAttention and quantized-path optimizations.

  • LinearAttention subgroup optimizations and larger tile_v with subgroup support (#28412, #28519).

  • GatherBlockQuantized gained 2-bit support (#28530).

  • Reliability and hardening fixes.

  • Fixes for out-of-bounds read risks in GatherBlockQuantized and Pad (#28718, #28721).
  • Fix for past_state == present_state buffer handling (#28753).
  • Fixes in QMoE numerical stability and SkipSimplifiedLayerNormalization bias behavior (#28434, #28427).

  • ConvTranspose weight shape validation improvement (#28524).

  • Graph-capture and buffer-management improvements.

  • Per-graph buffer manager and session-level buffer pool updates for graph capture reuse (#28260, #28761).

Note: This section was AI-generated. It may have inaccuracies.

Contributors

Thanks to everyone who contributed to the WebGPU EP (human contributors, alphabetical):

@apsonawane, @daijh, @edgchen1, @feich-ms, @GopalakrishnanN, @guschmue, @hariharans29, @HectorSVC, @jchen10, @qjia7, @tianleiwu, @xiaofeihan1, @xenova, @yuslepukhin.

Note: This list was compiled on a best-effort basis from PRs that touched WebGPU EP-specific paths and intentionally includes human contributors only, so it may not capture every contribution. If yours was missed, the omission is unintentional. Your work is no less appreciated.

Source: README.md, updated 2026-07-28