Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32)#25874
Draft
johnkarlhill wants to merge 2 commits into
Draft
Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32)#25874johnkarlhill wants to merge 2 commits into
johnkarlhill wants to merge 2 commits into
background
wait
wait-all
cancel
parallel
Loading