Charlie Ruan issues

Repositories
Issues
Comments

Results 13 issues of


                                            Charlie Ruan

[WebGPU] Support warp-level shuffle primitives with subgroup

### Overview This PR supports warp-level shuffle primitives using the newly introduced `subgroup` in WebGPU. We then use them in the implementation of allreduce lowering. The introduced primitives are: -...

Roadmap

### Function calling - [ ] Integrate with XGrammar's structural tag: https://github.com/mlc-ai/xgrammar/pull/162, and enable reliable tool use with small models in WebLLM - [ ] Add an E2E MCP-like example,...

[Web] Support structural tag for web-xgrammar package, update web to 0.1.18

This PR updates the web-xgrammar TypeScript package, mainly adding support for Structural Tag. There are two components to this PR: 1. Address trivial changes to the APIs, including adding `any_whitespace`...