Skip to content

MoE fp8 backward: in-kernel drhs operand quantization + configurable gradient dtype - #4971

Open
ultrons wants to merge 4 commits into
AI-Hypercomputer:test_964807349from
ultrons:sivaibhav-moe-bwd-inkernel-quant
Open

MoE fp8 backward: in-kernel drhs operand quantization + configurable gradient dtype#4971
ultrons wants to merge 4 commits into
AI-Hypercomputer:test_964807349from
ultrons:sivaibhav-moe-bwd-inkernel-quant

review: quantize only the dlhs cotangent on the in-kernel path; Liter…

a7bf842
Select commit
Loading
Failed to load commit list.
Google CLA / cla/google succeeded Aug 22, 2026 in 7s

✅ All contributors are covered under a CLA with Google

See https://cla.developers.google.com/ for more info about Google's Contributor License Agreement (CLA).

ℹ️ Googlers: Go here to view more details and manage scans for this pull request.

Details

The following contributors were found for this pull request:

✅ a7bf842 Author: @ultrons <si*****av​@google.com>

(Only the first commit for a unique contributor is listed.)

View more details on Google CLA