Masashi Yoshimura and GitHub
c40006a62e
ggml-webgpu: Fix how to dispatch WG to some ops ( #23750 )
2026-05-27 09:48:12 -07:00
Masashi Yoshimura and GitHub
1506d39e76
ggml-webgpu: Add MMVQ path for Q4/Q8/Q2_K/Q4_K and clean up legacy MUL_MAT pipeline ( #23594 )
...
* ggml-webgpu: Add MMVQ path for Q4/Q8/Q2_K/Q4_K
* Fix to editorconfig checking pass
* Remove mul-mat-legacy pipeline
* Fix to use vendor name as is and add dot_product/vendor to shader_lib_ctx
2026-05-25 20:42:49 -07:00
Masashi Yoshimura and GitHub
527045bfb0
flush the gpu profile timestamp before the queryset is overflowed ( #22995 )
2026-05-13 10:22:44 -07:00
Masashi Yoshimura and GitHub
927dada6c9
ggml-webgpu: Enables running gpt-oss-20b ( #22906 )
...
* Enable to run gpt-oss-20b and refactor mulmat-q
* disable test-backend-ops in ubuntu-24-webgpu
2026-05-12 07:27:40 -07:00
c3c1505392
ggml-webgpu: Fix vectorized handling in mul-mat and mul-mat-id ( #22578 )
...
* Fix vectorized condition of mul-mat-fast pipeline and add vectorized variant to mul-mat-id
* Apply suggestion from @CISC
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
2026-05-01 07:55:01 -07:00
Masashi Yoshimura and GitHub
a95a11e5b8
ggml-webgpu: Improve performance of mat-vec and mat-mat for MUL_MAT_ID ( #22464 )
...
* Add mat-vec fast path of MUL_MAT_ID.
* Add shared accumulation vec logic and the other types supports.
* Add i-quant mat-mat for MUL_MAT_ID and fix some parts
* Remove n_experts from shader_lib_context.
2026-04-30 14:19:10 -07:00
Masashi Yoshimura and GitHub
6da7168312
ggml-webgpu: Add fused RMS_NORM + MUL ( #21983 )
...
* fused rms_norm_mul + mul
* Add GGML_WEBGPU_DISABLE_FUSION for being able to disable kernel fusion.
* Decouple num_fused_ops from webgpu_context; misc cleanup
* Fix eps handling and remove disable_fusion.
* Fix not to use c++20 initializers.
2026-04-22 10:51:40 -07:00
Masashi Yoshimura and GitHub
2799d933b5
ggml-webgpu: reset CPU/GPU profiling time when freeing context ( #22050 )
...
* Reset the CPU/GPU profiling time when freeing context.
* move GPU profiling time from global context to webgpu_context.
2026-04-21 16:05:21 -07:00
Masashi Yoshimura and GitHub
bafae27654
Remove extra conditional check on debug mode. ( #21798 )
2026-04-12 20:13:04 -07:00
d0a6dfeb28
ggml-webgpu: Add the support of MUL_MAT_ID ( #21147 )
...
* Add mul_mat_id support to WebGPU
* Apply suggestion from @reeselevine
---------
Co-authored-by: Reese Levine <reeselevine1@gmail.com >
2026-04-06 13:08:46 -07:00
Masashi Yoshimura and GitHub
509a31d00f
ggml-webgpu: Update the RMS_NORM preprocessor and add L2_NORM ( #20665 )
...
* Update the preprocessor of RMS_NORM and add L2_NORM.
* Fix the name of rms_norm to row_norm.
2026-03-18 21:08:59 -07:00
Masashi Yoshimura and GitHub
ea01d196d7
ggml-webgpu: Add supports for DIAG and TRI ( #20664 )
...
* Add supports for DIAG and TRI.
* Remove extra ttype and add a comment for TRI op.
2026-03-18 21:08:35 -07:00
Masashi Yoshimura and GitHub
05039967da
ggml-virtgpu: Fix some build commands ( #20341 )
2026-03-12 15:47:45 +08:00
Masashi Yoshimura and GitHub
f2ab047f27
ggml-webgpu: Add supports for GGML_OP_REPEAT ( #20230 )
...
* Add GGML_OP_REPEAT to webgpu backend.
* Add i16 support for GGML_OP_REPEAT.
2026-03-11 14:40:36 -07:00
Masashi Yoshimura and GitHub
541bf37622
Add concat op to webgpu. ( #20068 )
2026-03-04 11:19:00 -08:00
Masashi Yoshimura and GitHub
36a7a6589c
ggml-webgpu: Support non-contiguous src0 and overlapping src0/src1 in binary ops ( #19850 )
...
* ggml-webgpu: Add binary op support for overlapping and non-contiguous.
* Add newline to binary.wgsl
* Append the test of binary op for src overlapping to test_bin_bcast.
* Remove unnecessary newline.
2026-03-02 07:59:53 -08:00
Masashi Yoshimura and GitHub
11c325c6e0
ggml-webgpu: Add unary op (SQR, SQRT, SIN, COS) support. ( #19700 )
...
* ggml-webgpu: Add unary op (SQR, SQRT, SIN, COS) support.
* Fix to cast the src value to f32 before sin/cos computing.
2026-02-19 09:18:30 -07:00
Masashi Yoshimura and GitHub
480160d472
ggml-webgpu: Fix GGML_MEM_ALIGN to 8 for emscripten. ( #18628 )
...
* Fix GGML_MEM_ALIGN to 8 for emscripten.
* Add a comment explaining the need for GGML_MEM_ALIGN == 8 in 64-bit wasm with emscripten
2026-01-08 08:36:42 -08:00
