Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model : add Tencent Hy 4 (hy_v4) preview architecture support (#28127)

Browse Source 
* model: add Tencent Hy 4 (hy_v4) preview architecture support

Adds support for the Tencent Hy 4 model (Hugging Face architecture
HYV4ForCausalLM, GGUF arch hy_v4):

Add HF -> GGUF conversion script (conversion/hy_v4.py) and wire it into the conversion registry
Register hy_v4 GGUF constants, arch enum, and writer support
Implement the hy-v4 model graph, hparams, vocab and context changes
Register the new arch in llama-arch and models registry
Extend arch tests to cover hy_v4

Assisted by Claude Opus 5

* Update convert_hf_to_gguf_update.py

Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>

* Update conversion/base.py

Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>

* convert : move hy_v4 entry to the same place as in convert_hf_to_gguf_update.py

* model : apply changes related to n_ff_exp becoming per-layer in Hy4-preview

* n_layer_all

---------

Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
This commit is contained in:
HongHuang
2026-09-04 14:31:36 +02:00
committed by GitHub
co-authored by fairydreaming Stanisław Szymczyk Sigbjørn Skjæret
parent 5266f24da7
commit 49c0dc82b8
18 changed files with 1124 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-graph.cpp
+5 -2
View File
@@ -566,7 +566,10 @@ void llm_graph_input_attn_k_dsa::set_input(const llama_ubatch * ubatch) {
mctx->get_lid()->set_input_kq_mask(self_kq_mask_lid, ubatch, cparams.causal_attn);
mctx->get_lid()->set_input_k_rot(self_k_rot_lid);
// left unallocated when the indexer does not use the rotation
if (self_k_rot_lid && self_k_rot_lid->buffer) {
mctx->get_lid()->set_input_k_rot(self_k_rot_lid);
}
}
bool llm_graph_input_attn_k_dsa::can_reuse(const llm_graph_params & params) {
@@ -2170,7 +2173,7 @@ ggml_tensor * llm_graph_context::build_moe_ffn(
const float limit = hparams.swiglu_clamp_exp[il];
constexpr float eps = 1e-6f;
if (limit > eps) {
if (arch == LLM_ARCH_DEEPSEEK4 || (arch == LLM_ARCH_DFLASH && hparams.dsv4_hc_mult > 0)) {
if (arch == LLM_ARCH_DEEPSEEK4 || (arch == LLM_ARCH_DFLASH && hparams.dsv4_hc_mult > 0) || arch == LLM_ARCH_HY_V4) {
cur = ggml_swiglu_clamp(ctx0, cur, up, limit);
} else {
up = ggml_clamp(ctx0, up, -limit, limit);