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]
