wmantly/llama.cpp-xrip
1
0 Fork 0
Code Issues Pull Requests Actions 33 Packages Projects Releases Wiki Activity

Revert "MoE expert cache: GPU-resident LRU cache for host-offloaded expert weights"

Browse Source 
This reverts commit 7391a178e6.
This commit is contained in:
xrip committed 2026-10-08 08:07:34 +03:00
1 parent d7c332228f
commit dad523e050
12 files changed
-627
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

common/common.cpp
-2
View File
@@ -1719,8 +1719,6 @@ struct llama_context_params common_context_params_to_llama(const common_params &
cparams.n_outputs_max_per_seq = std::max(params.n_outputs_max_per_seq, 0);
cparams.n_batch = params.n_batch;
cparams.n_ubatch = params.n_ubatch;
cparams.n_moe_cache_slots = params.n_moe_cache_slots;
cparams.n_moe_cache_inserts = params.n_moe_cache_inserts;
cparams.n_threads = params.cpuparams.n_threads;
cparams.n_threads_batch = params.cpuparams_batch.n_threads == -1 ?
params.cpuparams.n_threads : params.cpuparams_batch.n_threads;