]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 96fdb90)
update HIP_UMA #7399 (llama/7414)
authorDjip007 <redacted>
Mon, 27 May 2024 23:40:47 +0000 (01:40 +0200)
committerGeorgi Gerganov <redacted>
Sun, 16 Jun 2024 15:19:48 +0000 (18:19 +0300)
commit68ef10805e7af2795b252b9443a06d66a4524150
treed9c0d9e819509efe6eddb840c66309c049f2b67btree
parent96fdb90f5fbf7c5576ac2b512ff36752e3f04badcommit | diff
update HIP_UMA #7399 (llama/7414)

* update HIP_UMA #7399

add use of hipMemAdviseSetCoarseGrain when LLAMA_HIP_UMA is enable.
- get x2 on prompte eval and x1.5 on token gen with rocm6.0 on ryzen 7940HX iGPU (780M/gfx1103)

* simplify code, more consistent style

---------

Co-authored-by: slaren <redacted>
ggml-cuda.cu diff | blob | history
ggml-cuda/common.cuh diff | blob | history
Packaging of ggerganov/whisper.cpp