The GitHub Actions job "tvm-bot" on tvm.git/main has succeeded.
Run started by GitHub user akaashrp (triggered by akaashrp).

Head commit for run:
27c2e019d0ce6182158020c7534dda4a3ce981ae / Akaash Parthasarathy 
<[email protected]>
[Feature][Relax] Support shared-KV attention with configurable sliding windows 
(#20121)

Extend `PagedKVCache` for models whose logical attention layers reuse
K/V cached by another physical layer.
- Adds non-mutating `attention_with_shared_kv` support.
- Makes per-layer sliding-window size configurable.
- Corrects sliding-window masking during chunked prefill.

This is intended to enable downstream Gemma 4 support in MLC-LLM and
WebLLM.

Report URL: https://github.com/apache/tvm/actions/runs/32019145452

With regards,
GitHub Actions via GitBox


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to