sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-12 12:04:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama: end-to-end tests (#19802)

Browse Source 
* tests: add end-to-end tests per model architecture

* fixup for rebase

* fix use-after-free in llama-model-loader.cpp

* fix CI

* fix WebGPU

* fix CI

* disable CI for macOS-latest-cmake-arm64

* use expert_weights_scale only if != 0.0f

* comments
This commit is contained in:
Johannes Gäßler
2026-03-08 12:30:21 +01:00
committed by GitHub
parent a95047979a
commit a976ff081b
33 changed files with 1607 additions and 633 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/models/plamo2.cpp
View File

@@ -27,7 +27,7 @@ llm_build_plamo2::llm_build_plamo2(const llama_model & model, const llm_graph_pa
cur = build_norm(inpL, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
// check if this layer is Mamba or Attention
bool is_mamba_layer = hparams.is_recurrent(il);
const bool is_mamba_layer = hparams.is_recurrent(il);
if (is_mamba_layer) {
// PLaMo-2 Mamba layer
@@ -171,6 +171,8 @@ ggml_tensor * llm_build_plamo2::build_plamo2_mamba_layer(llm_graph_input_rs * in
GGML_ASSERT(n_seqs != 0);
GGML_ASSERT(ubatch.equal_seqs());
GGML_ASSERT(ubatch.n_tokens == n_seq_tokens * n_seqs);
GGML_ASSERT(d_inner % n_head == 0);
GGML_ASSERT(n_group == 0);
ggml_tensor * conv_states_all = mctx_cur->get_r_l(il);
ggml_tensor * ssm_states_all = mctx_cur->get_s_l(il);