CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-09 10:17:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

model: add support for qwen3vl series (#16780)

Browse Source 
* support qwen3vl series.

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>

* bugfix: fix the arch check for qwen3vl-moe.

* use build_ffn

* optimize deepstack structure

* optimize deepstack feature saving

* Revert "optimize deepstack feature saving" for temporal fix

This reverts commit f321b9fdf1.

* code clean

* use fused qkv in clip

* clean up / rm is_deepstack_layers for simplification

* add test model

* move test model to "big" section

* fix imrope check

* remove trailing whitespace

* fix rope fail

* metal : add imrope support

* add imrope support for sycl

* vulkan: add imrope w/o check

* fix vulkan

* webgpu: add imrope w/o check

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix tensor mapping

---------

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
JJJYmmm
2025-10-30 23:19:14 +08:00
committed by GitHub
parent dcca0d3ab8
commit d261223d24
28 changed files with 1125 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
ggml/src/ggml-webgpu/wgsl-shaders/rope.tmpl.wgsl
View File

@@ -221,6 +221,7 @@ fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
let is_neox = bool(params.mode & 2);
let is_mrope = bool(params.mode & 8);
let is_imrope = params.mode == 40;
let is_vision = params.mode == 24;
var i = gid.x * 2; // start index for this thread
@@ -248,24 +249,36 @@ fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
let sec_w = params.sections1 + params.sections0;
let sec_e = params.sections2 + sec_w;
let sector = (i0 / 2) % sect_dims;
if (sector >= params.sections0 && sector < sec_w) {
theta_base_mult = 1;
if (is_vision) {
theta_scale_pwr = sector - params.sections0;
}
} else if (sector >= sec_w && sector < sec_e) {
theta_base_mult = 2;
if (is_vision) {
theta_scale_pwr = sector - sec_w;
}
} else if (sector >= sec_e) {
if (is_vision) {
theta_scale_pwr = sector - sec_e;
theta_scale_pwr = (i0 / 2) % sec_e;
}
theta_base_mult = 3;
} else if (is_vision) {
theta_scale_pwr = sector;
if (is_imrope) {
if (sector % 3 == 1 && sector < 3 * params.sections1) {
theta_base_mult = 1;
} else if (sector % 3 == 2 && sector < 3 * params.sections2) {
theta_base_mult = 2;
} else if (sector % 3 == 0 && sector < 3 * params.sections0) {
theta_base_mult = 0;
} else {
theta_base_mult = 3;
}
} else {
if (sector >= params.sections0 && sector < sec_w) {
theta_base_mult = 1;
if (is_vision) {
theta_scale_pwr = sector - params.sections0;
}
} else if (sector >= sec_w && sector < sec_e) {
theta_base_mult = 2;
if (is_vision) {
theta_scale_pwr = sector - sec_w;
}
} else if (sector >= sec_e) {
if (is_vision) {
theta_scale_pwr = sector - sec_e;
theta_scale_pwr = (i0 / 2) % sec_e;
}
theta_base_mult = 3;
} else if (is_vision) {
theta_scale_pwr = sector;
}
}
}
let theta_base = f32(src1[params.offset_src1 + i2 + params.ne2 * theta_base_mult]) * pow(params.theta_scale, f32(theta_scale_pwr));