]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model...
authorChangyeon Kim <redacted>
Tue, 29 Oct 2024 08:52:56 +0000 (17:52 +0900)
committerGitHub <redacted>
Tue, 29 Oct 2024 08:52:56 +0000 (09:52 +0100)
commit8f275a7c4593aa34147595a90282cf950a853690
tree658952cf4c337a0beed4b272d449c2c93156c1cd
parent8d8ff715367480b856ad86ac3888e9742b13a6fa
ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. (#9763)

* ggml: Add POOL2D OP for GPU ACC to the Vulkan.

- The MobileVLM model now supports inference acceleration through GPU by utilizing the Vulkan backend.
- A GGML_OP_POOL_2D shader has been added. (Pooling)
- The encoding performance of the CLIP model improved from 2.8s on the CPU to 0.7s on the GPU.

Signed-off-by: Changyeon Kim <redacted>
* [fix] Correct the incorrect order of the parameters.

fix casting to int.

Signed-off-by: Changyeon Kim <redacted>
---------

Signed-off-by: Changyeon Kim <redacted>
ggml/src/ggml-vulkan.cpp
ggml/src/vulkan-shaders/pool2d.comp [new file with mode: 0644]
ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp