-
Notifications
You must be signed in to change notification settings - Fork 42
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
GEAK uses first GPU device regardless of top-level agent selection for xDiT run
domain:inferenceRelated to inference optimizationRelated to inference optimizationtype:bugSomething is broken or not working as expectedSomething is broken or not working as expectedStatus: Open.#1312 In AMD-AGI/Hyperloom;Online CI sees zero GEAK kernel gains while local runs see them - what differs between the two configurations?
awaiting-author-responseWaiting for issue author to reply (auto-managed)Waiting for issue author to reply (auto-managed)staleNo activity, scheduled for auto-closeNo activity, scheduled for auto-closeStatus: Open.#1311 In AMD-AGI/Hyperloom;- Status: Open.#1196 In AMD-AGI/Hyperloom;
Add RDNA4 GPU support (RX 9070 XT, RX 9070, RX 9060 XT, RX 9000 XT)
domain:inferenceRelated to inference optimizationRelated to inference optimizationdomain:trainingRelated to training optimizationRelated to training optimizationtype:featureNew capability or improvementNew capability or improvementStatus: Open.#1033 In AMD-AGI/Hyperloom;