]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
vulkan: optimize UMA buffer operations and fix driver hangs (llama/16059)
authorGiuseppe Scrivano <redacted>
Sun, 21 Sep 2025 06:31:55 +0000 (08:31 +0200)
committerGeorgi Gerganov <redacted>
Mon, 29 Sep 2025 12:18:08 +0000 (15:18 +0300)
commiteae2be0ca2118b8173eb0ee188134f02ebea581f
tree6805f7fee7156f84bdb787d792765fecaf7d8ec8
parent9a6c2036a9817e25fb61d66e8b4f2763ea98d195
vulkan: optimize UMA buffer operations and fix driver hangs (llama/16059)

* vulkan: optimize UMA buffer operations and fix driver hangs

The previous implementation was blocking the GPU for extended periods,
causing the i915 driver to reset the context due to the hangcheck
protection.

[32628.443070] i915 0000:00:02.0: [drm] GPU HANG: ecode 12:1:85dffffb, in llama-server [194114]
[32628.443091] i915 0000:00:02.0: [drm] llama-server[194114] context reset due to GPU hang

* vulkan: implement deferred_memset on UMA

---------

Signed-off-by: Giuseppe Scrivano <redacted>
ggml/src/ggml-vulkan/ggml-vulkan.cpp