CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: enable peer access between devices (#2470)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-09-17 16:37:53 +02:00
committed by GitHub
parent 8b428c9bc8
commit 111163e246
4 changed files with 63 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
Makefile
View File

@@ -368,6 +368,11 @@ ifdef LLAMA_CUDA_KQUANTS_ITER
else
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2
endif
ifdef LLAMA_CUDA_PEER_MAX_BATCH_SIZE
NVCCFLAGS += -DGGML_CUDA_PEER_MAX_BATCH_SIZE=$(LLAMA_CUDA_PEER_MAX_BATCH_SIZE)
else
NVCCFLAGS += -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128
endif # LLAMA_CUDA_PEER_MAX_BATCH_SIZE
#ifdef LLAMA_CUDA_CUBLAS
# NVCCFLAGS += -DGGML_CUDA_CUBLAS
#endif # LLAMA_CUDA_CUBLAS