]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml webgpu: quantized buffers to u32 + wider browser/device support (llama/21046)
authorReese Levine <redacted>
Wed, 1 Apr 2026 05:38:24 +0000 (22:38 -0700)
committerGeorgi Gerganov <redacted>
Wed, 1 Apr 2026 13:00:26 +0000 (16:00 +0300)
commit36b429c207704f435b08704c7fdd3c0e67acec56
tree3b611dc6be9cadffcbab2ee77c2f087a3df8577f
parentdff6d0945973e4436acedc8270aaad12e97d8774
ggml webgpu: quantized buffers to u32 + wider browser/device support (llama/21046)

* Work towards removing bitcast

* Move rest of existing types over

* Add timeout back to wait and remove synchronous set_tensor/memset_tensor

* move to unpackf16 for wider compatibility

* cleanup

* Remove deadlock condition in free_bufs
src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
src/ggml-webgpu/ggml-webgpu.cpp
src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl