Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 17:24:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

llama: give qwen4exp a large-graph node budget

Browse Source 
(cherry picked from commit 37c8c194e6a30e4c46ac29bee3fb264f091596ef)
This commit is contained in:
danielhanchen
2026-08-26 17:37:20 +00:00
committed by Daniel Han
parent 0ac4b18025
commit c52ed2a0b0
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+1
View File
@@ -2301,6 +2301,7 @@ uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const {
model.arch == LLM_ARCH_BAILINGMOE3 ||
model.arch == LLM_ARCH_QWEN35 ||
model.arch == LLM_ARCH_QWEN35MOE ||
model.arch == LLM_ARCH_QWEN4EXP ||
model.arch == LLM_ARCH_DEEPSEEK4 ||
(model.arch == LLM_ARCH_DFLASH && model.hparams.dsv4_hc_mult > 0) ||
model.arch == LLM_ARCH_NANBEIGE ||