ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 11:21:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix max nodes (again) (#1306)

Browse Source
This commit is contained in:
Kawrakow
2026-02-23 11:17:37 +01:00
committed by GitHub
parent 2bb40f8c35
commit 68bd30d99c
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-model.h
View File

@@ -430,8 +430,8 @@ struct llama_model {
if (arch == LLM_ARCH_QWEN3NEXT || arch == LLM_ARCH_QWEN35MOE) { if (arch == LLM_ARCH_QWEN3NEXT || arch == LLM_ARCH_QWEN35MOE) {
return std::max<size_t>(n_tokens * 40, 32u * n_tensors); return std::max<size_t>(n_tokens * 40, 32u * n_tensors);
} }
return std::max<size_t>(1024, 8*n_tensors); //return std::max<size_t>(1024, 8*n_tensors);
//return 65536 * 2; return 65536;
} }
bool has_tensor_overrides() const { bool has_tensor_overrides() const {