llama.cpp/docs
Reese Levine a89002f07b
ggml webgpu: support for backend sampling (#18880)
* ggml webgpu: add SOFTPLUS unary operator

Implements SOFTPLUS (log(1 + exp(x))) with f16/f32 support. Uses f32
precision for intermediate calculations to prevent f16 overflow.

* Add shader implementation and 4 variants (f32/f16, inplace/non-inplace)
* Register pipelines and device support
* Follow Vulkan backend numerical stability pattern

* ggml webgpu: add EXPM1 unary operator

Implements EXPM1 (exp(x) - 1) with f16/f32 support.

* Add shader implementation and 4 variants (f32/f16, inplace/non-inplace)
* Register pipelines and device support

* ggml webgpu: add FLOOR unary operator

Implements FLOOR (rounds down to nearest integer) with f16/f32 support.

* Add shader implementation and 4 variants (f32/f16, inplace/non-inplace)
* Register pipelines and device support

* ggml webgpu: add CEIL unary operator

Implements CEIL (rounds up to nearest integer) with f16/f32 support.

* Add shader implementation and 4 variants (f32/f16, inplace/non-inplace)
* Register pipelines and device support

* ggml webgpu: add ROUND unary operator

Implements ROUND (rounds to nearest integer) with f16/f32 support.

* Add shader implementation and 4 variants (f32/f16, inplace/non-inplace)
* Register pipelines and device support

* ggml webgpu: add TRUNC unary operator

Implements TRUNC (truncates towards zero) with f16/f32 support.

* Add shader implementation and 4 variants (f32/f16, inplace/non-inplace)
* Register pipelines and device support

* docs : update WebGPU support for unary operators (FLOOR, CEIL, ROUND, TRUNC, EXPM1, SOFTPLUS)

* Updates to webgpu get_memory

* Add argmax

* Add argmax,cumsum,sum,sum_rows

* Add necessary CPY/GET_ROWS operators

* Support for argsort using multi-pass strategy

* Update set_rows for i32 indices, move to pre-wgsl

* Port unary operators to pre-wgsl and support FILL

* Implement PAD

* Add support for top-k

* clean up, scope pipeline init mutex

* fix newline

* Add support for log

* Update LOG for better precision, and ops doc

---------

Co-authored-by: Abhijit Ramesh <abhijitramesh2k@gmail.com>
2026-01-16 16:12:43 -08:00
..
android android: fix missing screenshots for Android.md (#18156) 2025-12-19 09:32:04 +02:00
backend hexagon: support for OP_CPY, host buffers now optional, hvx-utils refactoring and optimizations (#18822) 2026-01-14 21:46:12 -08:00
development docs : fix links in parsing.md (#18245) 2025-12-21 09:35:40 +01:00
multimodal model : support MiniCPM-V 4.5 (#15575) 2025-08-26 10:05:55 +02:00
ops ggml webgpu: support for backend sampling (#18880) 2026-01-16 16:12:43 -08:00
android.md android: fix missing screenshots for Android.md (#18156) 2025-12-19 09:32:04 +02:00
build-riscv64-spacemit.md refactor : remove libcurl, use OpenSSL when available (#18828) 2026-01-14 18:02:47 +01:00
build-s390x.md ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free (#15839) 2025-09-13 02:39:52 +08:00
build.md refactor : remove libcurl, use OpenSSL when available (#18828) 2026-01-14 18:02:47 +01:00
docker.md CLI: fixed adding cli and completion into docker containers, improved docs (#18003) 2025-12-16 11:52:23 +01:00
function-calling.md common : implement new jinja template engine (#18462) 2026-01-16 11:22:06 +01:00
install.md docs : add "Quick start" section for new users (#13862) 2025-06-03 13:09:36 +02:00
llguidance.md llguidance build fixes for Windows (#11664) 2025-02-14 12:46:08 -08:00
multimodal.md mtmd : add support for Voxtral (#14862) 2025-07-28 15:01:48 +02:00
ops.md ggml webgpu: support for backend sampling (#18880) 2026-01-16 16:12:43 -08:00
preset.md preset: allow named remote preset (#18728) 2026-01-10 15:12:29 +01:00