Skip to content

[pull] master from ggml-org:master #191

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

Merged
pull merged 3 commits into from
Jul 22, 2025
Merged

[pull] master from ggml-org:master #191

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d4d1522
llama : add model type detection for rwkv7 7B&14B (#14816)
MollySophia Jul 22, 2025
84712b6
vulkan: fix rms_norm_mul to handle broadcasting dim0 (#14817)
jeffbolznv Jul 22, 2025
acd6cb1
ggml : model card yaml tab->2xspace (#14819)
csabakecskemeti Jul 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10248,7 +10248,7 @@ static bool ggml_vk_can_fuse(const struct ggml_cgraph * cgraph, int node_idx, st
}
// if rms_norm is the B operand, then we don't handle broadcast
if (rms_norm == mul->src[1] &&
mul->src[0]->ne[1] != rms_norm->ne[1]) {
!ggml_are_same_shape(mul->src[0], rms_norm)) {
return false;
}
// rms_norm shader assumes contiguous rows
Expand Down
10 changes: 8 additions & 2 deletions ggml/src/ggml-vulkan/vulkan-shaders/rms_norm.comp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,8 +50,14 @@ void main() {
const FLOAT_TYPE scale = inversesqrt(mean + FLOAT_TYPE(p.param1));

if (do_multiply) {
[[unroll]] for (uint col = tid; col < ncols; col += BLOCK_SIZE) {
data_d[d_offset + col] = D_TYPE(scale * FLOAT_TYPE(data_a[a_offset + col]) * FLOAT_TYPE(data_b[b_offset + col]));
if (ncols > p.ne10) {
[[unroll]] for (uint col = tid; col < ncols; col += BLOCK_SIZE) {
data_d[d_offset + col] = D_TYPE(scale * FLOAT_TYPE(data_a[a_offset + col]) * FLOAT_TYPE(data_b[b_offset + fastmod(col, p.ne10)]));
}
} else {
[[unroll]] for (uint col = tid; col < ncols; col += BLOCK_SIZE) {
data_d[d_offset + col] = D_TYPE(scale * FLOAT_TYPE(data_a[a_offset + col]) * FLOAT_TYPE(data_b[b_offset + col]));
}
}
} else {
[[unroll]] for (uint col = tid; col < ncols; col += BLOCK_SIZE) {
Expand Down
4 changes: 4 additions & 0 deletions gguf-py/gguf/metadata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,10 @@ def load_model_card(model_path: Optional[Path] = None) -> dict[str, Any]:
# Quick hack to fix the Norway problem
# https://hitchdev.com/strictyaml/why/implicit-typing-removed/
yaml_content = yaml_content.replace("- no\n", "- \"no\"\n")
# yaml should use 2 spaces insted of tab
# this issue has came up with the Qwen/Qwen3-235B-A22B-Instruct-2507 model card
# (I've also sent a pr tp fix the modelcard too)
yaml_content = yaml_content.replace("\t", " ")

if yaml_content:
data = yaml.safe_load(yaml_content)
Expand Down
18 changes: 16 additions & 2 deletions src/llama-model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1544,7 +1544,11 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_TOKEN_SHIFT_COUNT, hparams.token_shift_count, false);

switch (hparams.n_layer) {
case 12: type = LLM_TYPE_190M; break;
case 12:
switch (hparams.n_embd) {
case 768: type = LLM_TYPE_190M; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 24:
switch (hparams.n_embd) {
case 1024: type = LLM_TYPE_450M; break;
Expand All @@ -1557,7 +1561,17 @@ void llama_model::load_hparams(llama_model_loader & ml) {
case 3584: type = LLM_TYPE_7B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 32: type = LLM_TYPE_2_9B; break; // RWKV-7-World
case 32:
switch (hparams.n_embd) {
case 2560: type = LLM_TYPE_2_9B; break;
case 4096: type = LLM_TYPE_7B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 61:
switch (hparams.n_embd) {
case 4096: type = LLM_TYPE_14B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;
Expand Down
Loading