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

Head commit for run:
f8e5f6aa2916261b07c4fd4c3ac94bcf022de396 / Akaash Parthasarathy 
<[email protected]>
[Web] Decode packed BF16 tensor records in place (#20167)

Reduce peak WASM memory during BF16 tensor-cache loading by decoding
directly in the final `float32` CPU tensor allocation. The packed BF16
input is copied into the lower half of the destination tensor and
expanded backward, preventing output writes from overwriting unread
input. This removes the separate FFI byte-array allocation previously
required during decoding. Leave the existing decoder as a fallback when
the new WASM entry point is unavailable.

Report URL: https://github.com/apache/tvm/actions/runs/33114594197

With regards,
GitHub Actions via GitBox


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

Reply via email to