git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

author	Reese Levine <redacted>
	Thu, 4 Jun 2026 05:05:04 +0000 (22:05 -0700)
committer	GitHub <redacted>
	Thu, 4 Jun 2026 05:05:04 +0000 (08:05 +0300)
commit	e8c54893f2bbe356188ec4582ca44c233ae45127
tree	4890b4fb618b4a0c0312ec1921a7bc6046086a03	tree
parent	3c7450cee1335eef6f8091fa0498e875249e5595	commit \| diff

ggml-webgpu: FlashAttention refactor + standardize quantization support (#23834)

* Start work on flash_attn refactor

* Refactor

* Split k/v quantization

* Refactor and abstract quantization logic for flash_attn and mul_mat

* Add quantization support to tile path

* formatting

* Move to functions, add a check

Packaging of ggml-org/llama.cpp

RSS Atom

ggml/src/ggml-webgpu/CMakeLists.txt		diff \| blob \| history
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp		diff \| blob \| history
ggml/src/ggml-webgpu/ggml-webgpu.cpp		diff \| blob \| history
ggml/src/ggml-webgpu/pre_wgsl.hpp		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_quant_staging.tmpl	[new file with mode: 0644]	blob
ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/quant_inner_loops.tmpl	[new file with mode: 0644]	blob
tests/test-backend-ops.cpp		diff \| blob \| history