mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-25 07:58:01 +00:00
ggml update to b7108 (#12992)
* Revert "vulkan: temporary cary of vulkan fixes (#12971)"
This reverts commit 3a9e8e9fd4.
* ggml update to b7087
* fix argsort on metal
* update to b7108
* fix bakllava regression
This model lacks the metadata for the projector type.
* update to b7209
* fix TopK perf
* only build arm code on arm
This commit is contained in:
Daniel Hiltgen
@@ -6,108 +6,101 @@ Subject: [PATCH] interleave multi rope
|
||||
since ollama doesn't use mrope for anything else, change it to mean the
|
||||
interleaved version used for qwen3vl
|
||||
---
|
||||
ggml/src/ggml-cpu/ops.cpp | 7 ++-----
|
||||
ggml/src/ggml-cuda/rope.cu | 12 +++---------
|
||||
ggml/src/ggml-metal/ggml-metal.metal | 10 +++-------
|
||||
ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp | 12 +++---------
|
||||
4 files changed, 11 insertions(+), 30 deletions(-)
|
||||
ggml/src/ggml-cpu/ops.cpp | 8 ++++----
|
||||
ggml/src/ggml-cuda/rope.cu | 8 ++++----
|
||||
ggml/src/ggml-metal/ggml-metal.metal | 8 ++++----
|
||||
ggml/src/ggml-vulkan/vulkan-shaders/rope_funcs.glsl | 8 ++++----
|
||||
4 files changed, 16 insertions(+), 16 deletions(-)
|
||||
|
||||
diff --git a/ggml/src/ggml-cpu/ops.cpp b/ggml/src/ggml-cpu/ops.cpp
|
||||
index 902fdad69..70955347d 100644
|
||||
index 40666bab6..3155cb4bb 100644
|
||||
--- a/ggml/src/ggml-cpu/ops.cpp
|
||||
+++ b/ggml/src/ggml-cpu/ops.cpp
|
||||
@@ -5509,15 +5509,12 @@ static void ggml_mrope_cache_init(
|
||||
}
|
||||
@@ -5599,14 +5599,14 @@ static void ggml_mrope_cache_init(
|
||||
|
||||
float theta = theta_t;
|
||||
- if (sector >= sections[0] && sector < sec_w) {
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * sections[1]) {
|
||||
theta = theta_h;
|
||||
}
|
||||
- else if (sector >= sec_w && sector < sec_w + sections[2]) {
|
||||
+ else if (sector % 3 == 2 && sector < 2 + 3 * sections[2]) {
|
||||
theta = theta_w;
|
||||
}
|
||||
- else if (sector >= sec_w + sections[2]) {
|
||||
- theta = theta_e;
|
||||
- }
|
||||
|
||||
rope_yarn(
|
||||
theta/ff, freq_scale, corr_dims, i0, ext_factor, mscale, &cache[i0 + 0], &cache[i0 + 1]
|
||||
if (is_imrope) { // qwen3vl apply interleaved mrope
|
||||
- if (sector % 3 == 1 && sector < 3 * sections[1]) {
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * sections[1]) {
|
||||
theta = theta_h;
|
||||
- } else if (sector % 3 == 2 && sector < 3 * sections[2]) {
|
||||
+ } else if (sector % 3 == 2 && sector < 2 + 3 * sections[2]) {
|
||||
theta = theta_w;
|
||||
} else if (sector % 3 == 0 && sector < 3 * sections[0]) {
|
||||
theta = theta_t;
|
||||
- } else {
|
||||
- theta = theta_e;
|
||||
+ // } else {
|
||||
+ // theta = theta_e;
|
||||
}
|
||||
} else {
|
||||
if (sector >= sections[0] && sector < sec_w) {
|
||||
diff --git a/ggml/src/ggml-cuda/rope.cu b/ggml/src/ggml-cuda/rope.cu
|
||||
index d058504cd..287fe9d2c 100644
|
||||
index 88ed79111..71ca60214 100644
|
||||
--- a/ggml/src/ggml-cuda/rope.cu
|
||||
+++ b/ggml/src/ggml-cuda/rope.cu
|
||||
@@ -151,19 +151,13 @@ static __global__ void rope_multi(
|
||||
const int sec_w = sections.v[1] + sections.v[0];
|
||||
const int sector = (i0 / 2) % sect_dims;
|
||||
|
||||
- float theta_base = 0.0;
|
||||
- if (sector < sections.v[0]) {
|
||||
- theta_base = pos[channel_x]*powf(theta_scale, i0/2.0f);
|
||||
- }
|
||||
- else if (sector >= sections.v[0] && sector < sec_w) {
|
||||
+ float theta_base = pos[channel_x]*powf(theta_scale, i0/2.0f);
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * sections.v[1]) {
|
||||
theta_base = pos[channel_x + ne2 * 1]*powf(theta_scale, i0/2.0f);
|
||||
}
|
||||
- else if (sector >= sec_w && sector < sec_w + sections.v[2]) {
|
||||
+ else if (sector % 3 == 2 && sector < 2 + 3 * sections.v[2]) {
|
||||
theta_base = pos[channel_x + ne2 * 2]*powf(theta_scale, i0/2.0f);
|
||||
}
|
||||
- else if (sector >= sec_w + sections.v[2]) {
|
||||
- theta_base = pos[channel_x + ne2 * 3]*powf(theta_scale, i0/2.0f);
|
||||
- }
|
||||
|
||||
const float freq_factor = has_ff ? freq_factors[i0/2] : 1.0f;
|
||||
@@ -200,14 +200,14 @@ static __global__ void rope_multi(
|
||||
|
||||
float theta_base = 0.0;
|
||||
if (is_imrope) {
|
||||
- if (sector % 3 == 1 && sector < 3 * sections.v[1]) { // h
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * sections.v[1]) { // h
|
||||
theta_base = pos[channel_x + ne2 * 1]*powf(theta_scale, i0/2.0f);
|
||||
- } else if (sector % 3 == 2 && sector < 3 * sections.v[2]) { // w
|
||||
+ } else if (sector % 3 == 2 && sector < 2 + 3 * sections.v[2]) { // w
|
||||
theta_base = pos[channel_x + ne2 * 2]*powf(theta_scale, i0/2.0f);
|
||||
} else if (sector % 3 == 0 && sector < 3 * sections.v[0]) { // t
|
||||
theta_base = pos[channel_x]*powf(theta_scale, i0/2.0f);
|
||||
- } else {
|
||||
- theta_base = pos[channel_x + ne2 * 3]*powf(theta_scale, i0/2.0f);
|
||||
+ // } else {
|
||||
+ // theta_base = pos[channel_x + ne2 * 3]*powf(theta_scale, i0/2.0f);
|
||||
}
|
||||
} else {
|
||||
if (sector < sections.v[0]) {
|
||||
diff --git a/ggml/src/ggml-metal/ggml-metal.metal b/ggml/src/ggml-metal/ggml-metal.metal
|
||||
index 50b8071de..65a3183c8 100644
|
||||
index aed013a9d..a489de435 100644
|
||||
--- a/ggml/src/ggml-metal/ggml-metal.metal
|
||||
+++ b/ggml/src/ggml-metal/ggml-metal.metal
|
||||
@@ -3888,15 +3888,11 @@ kernel void kernel_rope_multi(
|
||||
const int sec_w012 = args.sect_0 + args.sect_1 + args.sect_2; // end of section 2
|
||||
const int sector = ic % sect_dims;
|
||||
@@ -4009,14 +4009,14 @@ kernel void kernel_rope_multi(
|
||||
|
||||
- float theta_base;
|
||||
- if (sector < args.sect_0) {
|
||||
- theta_base = (float) pos[i2];
|
||||
- } else if (sector < sec_w01) {
|
||||
+ float theta_base = (float) pos[i2];
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * args.sect_1) {
|
||||
theta_base = (float) pos[i2 + args.ne02];
|
||||
- } else if (sector < sec_w012) {
|
||||
+ } else if (sector % 3 == 2 && sector < 2 + 3 * args.sect_2) {
|
||||
theta_base = (float) pos[i2 + args.ne02 * 2];
|
||||
- } else {
|
||||
- theta_base = (float) pos[i2 + args.ne02 * 3];
|
||||
}
|
||||
// end of mrope
|
||||
|
||||
diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp b/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp
|
||||
index 111286b49..633dc20ff 100644
|
||||
--- a/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp
|
||||
+++ b/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp
|
||||
@@ -31,19 +31,13 @@ void main() {
|
||||
const int sec_w = p.sections[1] + p.sections[0];
|
||||
const uint sector = (i0 / 2) % sect_dims;
|
||||
|
||||
- float theta_base = 0.0;
|
||||
- if (sector < p.sections[0]) {
|
||||
- theta_base = data_pos[channel_x]*pow(p.theta_scale, i0/2.0f);
|
||||
- }
|
||||
- else if (sector >= p.sections[0] && sector < sec_w) {
|
||||
+ float theta_base = data_pos[channel_x]*pow(p.theta_scale, i0/2.0f);
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * p.sections[1]) {
|
||||
theta_base = data_pos[channel_x + ne2 * 1]*pow(p.theta_scale, i0/2.0f);
|
||||
}
|
||||
- else if (sector >= sec_w && sector < sec_w + p.sections[2]) {
|
||||
+ else if (sector % 3 == 2 && sector < 2 + 3 * p.sections[2]) {
|
||||
theta_base = data_pos[channel_x + ne2 * 2]*pow(p.theta_scale, i0/2.0f);
|
||||
}
|
||||
- else if (sector >= sec_w + p.sections[2]) {
|
||||
- theta_base = data_pos[channel_x + ne2 * 3]*pow(p.theta_scale, i0/2.0f);
|
||||
- }
|
||||
|
||||
const float freq_factor = p.has_ff != 0 ? data_ff[i0/2] : 1.0f;
|
||||
float theta_base;
|
||||
if (FC_rope_is_imrope) {
|
||||
- if (sector % 3 == 1 && sector < 3 * args.sect_1) { // h
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * args.sect_1) { // h
|
||||
theta_base = (float) pos[i2 + args.ne02 * 1];
|
||||
- } else if (sector % 3 == 2 && sector < 3 * args.sect_2) { // w
|
||||
+ } else if (sector % 3 == 2 && sector < 2 + 3 * args.sect_2) { // w
|
||||
theta_base = (float) pos[i2 + args.ne02 * 2];
|
||||
} else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
|
||||
theta_base = (float) pos[i2 + args.ne02 * 0];
|
||||
- } else { // e
|
||||
- theta_base = (float) pos[i2 + args.ne02 * 3];
|
||||
+ // } else { // e
|
||||
+ // theta_base = (float) pos[i2 + args.ne02 * 3];
|
||||
}
|
||||
} else {
|
||||
if (sector < args.sect_0) {
|
||||
diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/rope_funcs.glsl b/ggml/src/ggml-vulkan/vulkan-shaders/rope_funcs.glsl
|
||||
index 9726b722d..1c8c69422 100644
|
||||
--- a/ggml/src/ggml-vulkan/vulkan-shaders/rope_funcs.glsl
|
||||
+++ b/ggml/src/ggml-vulkan/vulkan-shaders/rope_funcs.glsl
|
||||
@@ -148,14 +148,14 @@ void rope_multi(const uint i0, const uint i1, rope_params p) {
|
||||
|
||||
float theta_base = 0.0;
|
||||
if (p.is_imrope != 0) {
|
||||
- if (sector % 3 == 1 && sector < 3 * p.sections[1]) {
|
||||
+ if (sector % 3 == 1 && sector < 1 + 3 * p.sections[1]) {
|
||||
theta_base = rope_data_pos[i02 + ne2 * 1]*pow(p.theta_scale, i0/2.0f);
|
||||
- } else if (sector % 3 == 2 && sector < 3 * p.sections[2]) {
|
||||
+ } else if (sector % 3 == 2 && sector < 2 + 3 * p.sections[2]) {
|
||||
theta_base = rope_data_pos[i02 + ne2 * 2]*pow(p.theta_scale, i0/2.0f);
|
||||
} else if (sector % 3 == 0 && sector < 3 * p.sections[0]) {
|
||||
theta_base = rope_data_pos[i02]*pow(p.theta_scale, i0/2.0f);
|
||||
- } else {
|
||||
- theta_base = rope_data_pos[i02 + ne2 * 3]*pow(p.theta_scale, i0/2.0f);
|
||||
+ //} else {
|
||||
+ // theta_base = rope_data_pos[i02 + ne2 * 3]*pow(p.theta_scale, i0/2.0f);
|
||||
}
|
||||
} else {
|
||||
if (sector < p.sections[0]) {
|
||||
|
||||
Reference in New Issue
Block a user