]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
ggml-webgpu: Improve prefill speeds for k-quants + refactor matmul for Q4/Q5/Q8 and...
authorMasashi Yoshimura <redacted>
Mon, 8 Jun 2026 22:19:56 +0000 (07:19 +0900)
committerGeorgi Gerganov <redacted>
Mon, 15 Jun 2026 07:33:53 +0000 (10:33 +0300)
commitaa42b48312f28f31a84840d51bcc783380b00d03
tree6fe902ff263cf09bbf95837112ac606e83fb0f43
parent15e5d401d18dae5968d98ef54241317d5b8bab33
ggml-webgpu: Improve prefill speeds for k-quants + refactor matmul for Q4/Q5/Q8 and k-quants (llama/24225)

* ggml-webgpu: Improve prefill speeds + refactor matmul for quants

* Fixes for editroconfig checker
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl