mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 31 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 f321b9fdf13e59527408152e73b1071e19a87e71.

* 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
ggml/src/ggml-sycl/rope.cpp
+30 -17
View File
@@ -119,7 +119,7 @@ static void rope_multi(const T * x, T * dst, const int ne0, const int ne1, const
const size_t s2, const int n_dims, const int32_t * pos, const float freq_scale,
const float ext_factor, const float attn_factor, const rope_corr_dims corr_dims,
const float theta_scale, const float * freq_factors, const mrope_sections sections,
const sycl::nd_item<3> & item_ct1) {
const bool is_imrope, const sycl::nd_item<3> & item_ct1) {
// get index pos
const int i0 = 2 * (item_ct1.get_group(1) * item_ct1.get_local_range(1) + item_ct1.get_local_id(1));
if (i0 >= ne0) {
@@ -143,17 +143,29 @@ static void rope_multi(const T * x, T * dst, const int ne0, const int ne1, const
float theta_base = 0.0;
if (sector < sections.v[0]) {
theta_base = pos[channel_x]*sycl::pow(theta_scale, i0/2.0f);
}
else if (sector >= sections.v[0] && sector < sec_w) {
theta_base = pos[channel_x + ne2 * 1]*sycl::pow(theta_scale, i0/2.0f);
}
else if (sector >= sec_w && sector < sec_w + sections.v[2]) {
theta_base = pos[channel_x + ne2 * 2]*sycl::pow(theta_scale, i0/2.0f);
}
else if (sector >= sec_w + sections.v[2]) {
theta_base = pos[channel_x + ne2 * 3]*sycl::pow(theta_scale, i0/2.0f);
if (is_imrope) {
if (sector % 3 == 1 && sector < 3 * sections.v[1]) {
theta_base = pos[channel_x + ne2 * 1]*sycl::pow(theta_scale, i0/2.0f);
} else if (sector % 3 == 2 && sector < 3 * sections.v[2]) {
theta_base = pos[channel_x + ne2 * 2]*sycl::pow(theta_scale, i0/2.0f);
} else if (sector % 3 == 0 && sector < 3 * sections.v[0]) {
theta_base = pos[channel_x]*sycl::pow(theta_scale, i0/2.0f);
} else {
theta_base = pos[channel_x + ne2 * 3]*sycl::pow(theta_scale, i0/2.0f);
}
} else {
if (sector < sections.v[0]) {
theta_base = pos[channel_x]*sycl::pow(theta_scale, i0/2.0f);
}
else if (sector >= sections.v[0] && sector < sec_w) {
theta_base = pos[channel_x + ne2 * 1]*sycl::pow(theta_scale, i0/2.0f);
}
else if (sector >= sec_w && sector < sec_w + sections.v[2]) {
theta_base = pos[channel_x + ne2 * 2]*sycl::pow(theta_scale, i0/2.0f);
}
else if (sector >= sec_w + sections.v[2]) {
theta_base = pos[channel_x + ne2 * 3]*sycl::pow(theta_scale, i0/2.0f);
}
}
const float freq_factor = has_ff ? freq_factors[i0 / 2] : 1.0f;
@@ -281,7 +293,7 @@ static void rope_multi_sycl(const T * x, T * dst, const int ne0, const int ne1,
const size_t s2, const int n_dims, const int nr, const int32_t * pos,
const float freq_scale, const float freq_base, const float ext_factor,
const float attn_factor, const rope_corr_dims corr_dims, const float * freq_factors,
const mrope_sections sections, queue_ptr stream) {
const mrope_sections sections, const bool is_imrope, queue_ptr stream) {
GGML_ASSERT(ne0 % 2 == 0);
const sycl::range<3> block_dims(1, SYCL_ROPE_BLOCK_SIZE, 1);
const int n_blocks_y = ceil_div(ne0, (2 * SYCL_ROPE_BLOCK_SIZE));
@@ -297,12 +309,12 @@ static void rope_multi_sycl(const T * x, T * dst, const int ne0, const int ne1,
if (freq_factors == nullptr) {
stream->parallel_for(nd_range, [=](sycl::nd_item<3> item_ct1) {
rope_multi<T, false>(x, dst, ne0, ne1, ne2, s1, s2, n_dims, pos, freq_scale, ext_factor, attn_factor,
corr_dims, theta_scale, freq_factors, sections, item_ct1);
corr_dims, theta_scale, freq_factors, sections, is_imrope, item_ct1);
});
} else {
stream->parallel_for(nd_range, [=](sycl::nd_item<3> item_ct1) {
rope_multi<T, true>(x, dst, ne0, ne1, ne2, s1, s2, n_dims, pos, freq_scale, ext_factor, attn_factor,
corr_dims, theta_scale, freq_factors, sections, item_ct1);
corr_dims, theta_scale, freq_factors, sections, is_imrope, item_ct1);
});
}
}
@@ -381,6 +393,7 @@ inline void ggml_sycl_op_rope(ggml_backend_sycl_context & ctx, ggml_tensor *dst)
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) {
@@ -422,11 +435,11 @@ inline void ggml_sycl_op_rope(ggml_backend_sycl_context & ctx, ggml_tensor *dst)
if (dst->src[0]->type == GGML_TYPE_F16) {
rope_multi_sycl((const sycl::half *)dst->src[0]->data, (sycl::half *)dst->data, ne00, ne01, ne02, s01,
s02, n_dims, nr, pos, freq_scale, freq_base, ext_factor, attn_factor, corr_dims,
freq_factors, sections, main_stream);
freq_factors, sections, is_imrope, main_stream);
} else if (dst->src[0]->type == GGML_TYPE_F32) {
rope_multi_sycl((const float *) dst->src[0]->data, (float *) dst->data, ne00, ne01, ne02, s01, s02, n_dims,
nr, pos, freq_scale, freq_base, ext_factor, attn_factor, corr_dims, freq_factors, sections,
main_stream);
is_imrope, main_stream);
} else {
GGML_ABORT("Fatal error: Tensor type unsupported!");
}