]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
overview / pkg / ggml / sources / ggml / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: e31cd3a)
update HIP_UMA #7399 (llama/7414)
authorDjip007 <redacted>
Mon, 27 May 2024 23:40:47 +0000 (01:40 +0200)
committerGeorgi Gerganov <redacted>
Wed, 29 May 2024 10:16:38 +0000 (13:16 +0300)
commit686c48852afb9271971ef2b332051f7af086267f
treeec3329fe194a916503dd1335802a7a21463a9685tree
parente31cd3a07647ecf75a8ffb8cb78b17c51ce37d2acommit | 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>
src/ggml-cuda.cu diff | blob | history
src/ggml-cuda/common.cuh diff | blob | history
Packaging of ggml-org/ggml