ggml-webgpu : refactor several wgsl files and simplify flash_attn wgsl. (#26134) · f401bb1390 - llama.cpp - Gitea: Git with a cup of tea

Lumpiasty/llama.cpp

ggml-webgpu : refactor several wgsl files and simplify flash_attn wgsl. (#26134)

This commit is contained in:

Masashi Yoshimura

2026-08-10 09:29:41 +03:00

committed by

GitHub

parent 74ce15741b

commit f401bb1390

17 changed files with 372 additions and 862 deletions

									
										ggml/src/ggml-webgpu/wgsl-shaders/concat.wgsl
									
		-1
	
												View File
												
				@@ -18,7 +18,6 @@ struct Params {

				    ne0: u32,

				    ne1: u32,

				    ne2: u32,

				    ne3: u32,

				    dim: u32,

				    src0_nedim: u32