CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +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

36
ggml/src/ggml-cpu/ops.cpp
View File

@@ -5474,7 +5474,7 @@ static void ggml_rope_cache_init(
}
static void ggml_mrope_cache_init(
float theta_base_t, float theta_base_h, float theta_base_w, float theta_base_e, int sections[4], bool indep_sects,
float theta_base_t, float theta_base_h, float theta_base_w, float theta_base_e, int sections[4], bool is_imrope, bool indep_sects,
float freq_scale, const float * freq_factors, float corr_dims[2], int64_t ne0, float ext_factor, float mscale,
float * cache, float sin_sign, float theta_scale) {
// ref: https://github.com/jquesnelle/yarn/blob/master/scaled_rope/LlamaYaRNScaledRotaryEmbedding.py
@@ -5509,14 +5509,26 @@ static void ggml_mrope_cache_init(
}
float theta = theta_t;
if (sector >= sections[0] && sector < sec_w) {
theta = theta_h;
}
else if (sector >= sec_w && sector < sec_w + sections[2]) {
theta = theta_w;
}
else if (sector >= sec_w + sections[2]) {
theta = theta_e;
if (is_imrope) { // qwen3vl apply interleaved mrope
if (sector % 3 == 1 && sector < 3 * sections[1]) {
theta = theta_h;
} else if (sector % 3 == 2 && sector < 3 * sections[2]) {
theta = theta_w;
} else if (sector % 3 == 0 && sector < 3 * sections[0]) {
theta = theta_t;
} else {
theta = theta_e;
}
} else {
if (sector >= sections[0] && sector < sec_w) {
theta = theta_h;
}
else if (sector >= sec_w && sector < sec_w + sections[2]) {
theta = theta_w;
}
else if (sector >= sec_w + sections[2]) {
theta = theta_e;
}
}
rope_yarn(
@@ -5589,6 +5601,7 @@ static void ggml_compute_forward_rope_f32(
const bool is_neox = mode & GGML_ROPE_TYPE_NEOX;
const bool is_mrope = mode & GGML_ROPE_TYPE_MROPE; // ggml_rope_multi, multimodal rotary position embedding
const bool is_imrope = mode == GGML_ROPE_TYPE_IMROPE; // qwen3vl apply interleaved mrope
const bool is_vision = mode == GGML_ROPE_TYPE_VISION;
if (is_mrope) {
@@ -5627,7 +5640,7 @@ static void ggml_compute_forward_rope_f32(
const int64_t p_w = pos[i2 + ne2 * 2];
const int64_t p_e = pos[i2 + ne2 * 3];
ggml_mrope_cache_init(
p_t, p_h, p_w, p_e, sections, is_vision,
p_t, p_h, p_w, p_e, sections, is_imrope, is_vision,
freq_scale, freq_factors, corr_dims, ne0, ext_factor, attn_factor, cache, sin_sign, theta_scale);
}
@@ -5775,6 +5788,7 @@ static void ggml_compute_forward_rope_f16(
const bool is_neox = mode & GGML_ROPE_TYPE_NEOX;
const bool is_mrope = mode & GGML_ROPE_TYPE_MROPE;
const bool is_imrope = mode == GGML_ROPE_TYPE_IMROPE;
const bool is_vision = mode == GGML_ROPE_TYPE_VISION;
if (is_mrope) {
@@ -5813,7 +5827,7 @@ static void ggml_compute_forward_rope_f16(
const int64_t p_w = pos[i2 + ne2 * 2];
const int64_t p_e = pos[i2 + ne2 * 3];
ggml_mrope_cache_init(
p_t, p_h, p_w, p_e, sections, is_vision,
p_t, p_h, p_w, p_e, sections, is_imrope, is_vision,
freq_scale, freq_factors, corr_dims, ne0, ext_factor, attn_factor, cache, sin_sign, theta_scale);
}