Skip to content

vulkan: fuse rms_norm + mul + rope (+ view + set_rows) #16977

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

vulkan: fuse rms_norm + mul + rope (+ view + set_rows) #16977

wants to merge 1 commit into from

Conversation

@jeffbolznv
Copy link
Collaborator

@jeffbolznv jeffbolznv commented Nov 3, 2025

This change combines the rms_norm+mul and rope+view+set_rows fusions to allow fusing the whole sequence together. This comes up in Qwen3, Bailing, and some other models.

Helps a couple percent on models where it applies.

before:

Z:\github\jeffbolznv\llama.cpp\build\bin\RelWithDebInfo>llama-bench.exe -fa 1 -n 128,128,128,128,128 -p 0 -r 20 --prio 1 -m c:\models\Qwen_Qwen3-30B-A3B-Q4_K_M.gguf
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 5090 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
| model                          |       size |     params | backend    | ngl | fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |       269.45 ± 11.28 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        271.92 ± 3.88 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        273.37 ± 1.46 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        274.13 ± 1.33 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        274.37 ± 1.21 |

build: 1ae74882f (6913)

Z:\github\jeffbolznv\llama.cpp\build\bin\RelWithDebInfo>llama-bench.exe -fa 1 -n 128,128,128,128,128 -p 0 -r 20 --prio 1 -m c:\models\Qwen3-14B-Q4_K_M.gguf
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 5090 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
| model                          |       size |     params | backend    | ngl | fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        134.55 ± 3.63 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        133.55 ± 0.32 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        133.51 ± 0.51 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        133.49 ± 0.43 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        133.57 ± 0.33 |

build: 1ae74882f (6913)

Z:\github\jeffbolznv\llama.cpp\build\bin\RelWithDebInfo>llama-bench.exe -fa 1 -n 128,128,128,128,128 -p 0 -r 20 --prio 1 -m c:\models\Ring-mini-2.0-Q4_K_M.gguf
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 5090 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
| model                          |       size |     params | backend    | ngl | fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |       472.71 ± 38.19 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |       478.29 ± 10.31 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |       468.20 ± 16.25 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |        483.64 ± 2.21 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |        484.80 ± 2.20 |

build: 1ae74882f (6913)

after:

Z:\github\jeffbolznv\llama.cpp\build\bin\RelWithDebInfo>llama-bench.exe -fa 1 -n 128,128,128,128,128 -p 0 -r 20 --prio 1 -m c:\models\Qwen_Qwen3-30B-A3B-Q4_K_M.gguf
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 5090 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
| model                          |       size |     params | backend    | ngl | fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |       269.94 ± 17.36 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        275.08 ± 2.82 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        276.42 ± 1.60 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        276.48 ± 1.57 |
| qwen3moe 30B.A3B Q4_K - Medium |  17.35 GiB |    30.53 B | Vulkan     |  99 |  1 |           tg128 |        277.64 ± 0.90 |

build: b74de9b7b (6915)

Z:\github\jeffbolznv\llama.cpp\build\bin\RelWithDebInfo>llama-bench.exe -fa 1 -n 128,128,128,128,128 -p 0 -r 20 --prio 1 -m c:\models\Qwen3-14B-Q4_K_M.gguf
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 5090 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
| model                          |       size |     params | backend    | ngl | fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        137.12 ± 3.41 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        137.25 ± 3.01 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        138.57 ± 0.47 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        138.33 ± 0.56 |
| qwen3 14B Q4_K - Medium        |   8.38 GiB |    14.77 B | Vulkan     |  99 |  1 |           tg128 |        138.56 ± 0.53 |

build: b74de9b7b (6915)

Z:\github\jeffbolznv\llama.cpp\build\bin\RelWithDebInfo>llama-bench.exe -fa 1 -n 128,128,128,128,128 -p 0 -r 20 --prio 1 -m c:\models\Ring-mini-2.0-Q4_K_M.gguf
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 5090 (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
| model                          |       size |     params | backend    | ngl | fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |       482.35 ± 47.67 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |       488.51 ± 11.51 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |        487.90 ± 6.93 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |        494.89 ± 4.11 |
| bailingmoe2 16B.A1B Q4_K - Medium |   9.22 GiB |    16.26 B | Vulkan     |  99 |  1 |           tg128 |        496.09 ± 5.04 |

build: b74de9b7b (6915)

@github-actions github-actions bot added testing Everything test related Vulkan Issues specific to the Vulkan backend ggml changes relating to the ggml tensor library for machine learning labels Nov 3, 2025
jeffbolznv
jeffbolznv commented Nov 3, 2025
View reviewed changes
ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -14236,30 +14492,18 @@ size_t comp_size;
size_t comp_nb[GGML_MAX_DIMS];
size_t check_counter = 0;
static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx) {
Copy link
Collaborator Author

@jeffbolznv jeffbolznv Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The changes from here to the end of the file are the same as in #16919, I'll rebase once that lands.

@DajanaV DajanaV mentioned this pull request Nov 3, 2025
Closed
@jeffbolznv
vulkan: fuse rms_norm + mul + rope (+ view + set_rows)
7ca2c06 
This change combines the rms_norm+mul and rope+view+set_rows fusions to
allow fusing the whole sequence together. This comes up in Qwen3, Bailing,
and some other models.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@slaren slaren Awaiting requested review from slaren slaren is a code owner

@0cc4m 0cc4m Awaiting requested review from 0cc4m 0cc4m is a code owner

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@jeffbolznv