Bump @mlc-ai/web-llm from 0.2.85 to 0.2.86

[dependabot]

Bumps @mlc-ai/web-llm from 0.2.85 to 0.2.86.

Release notes

Sourced from @​mlc-ai/web-llm's releases.

v0.2.86

• Add Gemma 4 E2B instruction-tuned models in q4f16_1 and q4f32_1, with text and audio input. The FP32 variant does not require shader-f16.
• Update the bundled TVM runtime to @mlc-ai/web-runtime@0.28.0-dev0 and switch the prebuilt catalog to v0_2_86/base.
• Rebuild 224 WebGPU libraries: 112 each in base and sg32. The release includes compiler revisions, configuration snapshots, checksums, validation results, and a rebuild script.
• Use 4K-prefill Phi-3.5 vision libraries so default square images fit. The previous 2K variants remain in the binary folder.
• Include manifest-based audio and image loading, crash-resumable generation, and fixes for interrupted conversations, cancelled streams, model locks, token counts, and audio cleanup. Manifest loading remains optional; existing records retain the legacy path.

Artifacts:

• Gemma 4 E2B q4f16_1
• Gemma 4 E2B q4f32_1
• v0_2_86 model libraries and build provenance

Compiler sources: TVM be03dc94b0, based on Apache main 27576ce2d1 with a WebGPU FP32 prefill fix; MLC-LLM 42fa855891, based on main 8978ea9aec with compatibility updates for current TVM APIs.

Commits

• c42c366 [Release] WebLLM 0.2.86 with Gemma 4 E2B (#870)
• fb3a7fc [Fix] Close the audio adapter scope when its output is rejected (#867)
• 7f0f0d1 [Feature] Add image input for models that ship a manifest (#863)
• fa72210 [Fix] Rebuild the conversation after an interrupted or length-limited reply (...
• 506e1a6 [Fix] Clear a stale interrupt before a non-streaming request (#865)
• 317c1f8 [Fix] Count the prefill-sampled token in completion_tokens (#864)
• f997c52 [Docs] Shorten the audio section and a few comments (#862)
• 2fa759b [Feature] Add audio input for models that ship a manifest (#793)
• bd46399 [Docs] Fix copyright notice (#861)
• 442cecf [Example] Add crash-resumable generation demo (#860)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually 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 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)