Morph MORPH
SIGN IN SIGN UP
ggml-org / llama.cpp UNCLAIMED

LLM inference in C/C++

101214 0 0 C++

COMMITS

/ docs/ops/WebGPU.csv
master
March 19, 2026
R
ggml webgpu: ops support for qwen3.5 (SET, TRI_SOLVE, SSM_CONV, GATED_DELTA_NET) + GET_ROWS optimization (#20687)
Reese Levine committed
c125883
M
ggml-webgpu: Update the `RMS_NORM` preprocessor and add `L2_NORM` (#20665)
Masashi Yoshimura committed
509a31d
M
ggml-webgpu: Add supports for `DIAG` and `TRI` (#20664)
Masashi Yoshimura committed
ea01d19
March 11, 2026
M
ggml-webgpu: Add supports for `GGML_OP_REPEAT` (#20230)
Masashi Yoshimura committed
f2ab047
March 4, 2026
M
Add concat op to webgpu. (#20068)
Masashi Yoshimura committed
541bf37
February 19, 2026
M
ggml-webgpu: Add unary op (SQR, SQRT, SIN, COS) support. (#19700)
Masashi Yoshimura committed
11c325c
January 17, 2026
R
ggml webgpu: support for backend sampling (#18880)
Reese Levine committed
a89002f
January 5, 2026
N
ggml webgpu: add CEIL operation support (#18605)
nwyin committed
e443fbc
December 5, 2025
R
ggml webgpu: unary op suppport, code refactoring, ops support (#17764)
Reese Levine committed
fd57b24