v0.2.85

mlc-ai/web-llmv0.2.85Sep 8, 2026by akaashrp

AI Summary

This release updates the bundled TVM runtime and introduces synchronous OPFS access handles. It improves stability by preventing hangs and rejecting invalid parameters, while ensuring OpenAI-compatible API timestamps and preserving worker model state.

Key Highlights

Update bundled TVM web runtime to `0.27.0-dev0`
Add OPFS synchronous access handles and committed cache records
Register service-worker handlers to support restarted workers
Preserve recovered worker model state to avoid repeated reloads
Return OpenAI-compatible `created` timestamps in seconds

New Features

OPFS synchronous access handles and committed cache records
OpenAI-compatible `created` timestamps
Service-worker handler registration
Worker model state preservation

Full Release Notes

v0.2.85

- Add OPFS synchronous access handles and committed cache records, and update the bundled TVM web runtime to `0.27.0-dev0`.
- Return OpenAI-compatible `created` timestamps in seconds.
- Register service-worker handlers during startup so restarted workers can receive requests.
- Preserve recovered worker model state to avoid repeated reloads.
- Prevent hangs when initializing invalid structural-tag constraints.
- Reject NaN generation parameters.
- Render example output safely and correct cached-model `appConfig` examples.

This update continues to use the existing `v0_2_84/base` model libraries. No new model binaries are required by the validated paths.

Runtime source: [apache/tvm at 7e06fc6c1420d0188eb9d889bd74e2e1fb76e448](https://github.com/apache/tvm/commit/7e06fc6c1420d0188eb9d889bd74e2e1fb76e448).

Changes since the npm 0.2.84 source commit: [9e572d6...5f74244](https://github.com/mlc-ai/web-llm/compare/9e572d6ed95e248f29634996cd32cc8f3023d89d...5f742443179a5463e83a19f704d7c19f1f019f98).