wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

llama : add Gemma4 MTP (#23398)

Browse Source
This commit is contained in:
Aman Gupta
2026-06-07 20:50:54 +08:00
committed by GitHub
parent 8a091c47ab
commit 04eb4c446d
31 changed files with 644 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-llama-archs.cpp
+3 -3
View File
@@ -392,7 +392,7 @@ static bool arch_supported(const llm_arch arch) {
if (arch == LLM_ARCH_WAVTOKENIZER_DEC) {
return false; // FIXME CUDA backend crashes.
}
if (arch == LLM_ARCH_GEMMA4) {
if (arch == LLM_ARCH_GEMMA4 || arch == LLM_ARCH_GEMMA4_ASSISTANT) {
return false; // FIXME @ngxson
}
if (arch == LLM_ARCH_LLAMA_EMBED || arch == LLM_ARCH_GEMMA_EMBEDDING || arch == LLM_ARCH_T5ENCODER) {
@@ -447,7 +447,7 @@ static int save_models(const llm_arch target_arch, const size_t seed, const ggml
if (target_arch != LLM_ARCH_UNKNOWN && arch != target_arch) {
continue;
}
if (arch == LLM_ARCH_GEMMA4) {
if (arch == LLM_ARCH_GEMMA4 || arch == LLM_ARCH_GEMMA4_ASSISTANT) {
continue; // FIXME: ISWA KV cache initialization needs more fixture params
}
for (bool moe : {false, true}) {
@@ -550,7 +550,7 @@ static int test_backends(const llm_arch target_arch, const size_t seed, const gg
if (target_arch != LLM_ARCH_UNKNOWN && arch != target_arch) {
continue;
}
if (arch == LLM_ARCH_GEMMA4) {
if (arch == LLM_ARCH_GEMMA4 || arch == LLM_ARCH_GEMMA4_ASSISTANT) {
continue; // FIXME: ISWA KV cache initialization needs more fixture params
}