vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into gg/flash-attn

Browse source
This commit is contained in:
Georgi Gerganov 2024-04-25 15:50:36 +03:00
commit 1f77f49787
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
15 changed files with 1422 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.h
View file

@ -86,8 +86,8 @@ struct gpt_params {
ggml_numa_strategy numa = GGML_NUMA_STRATEGY_DISABLED;
llama_rope_scaling_type rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_UNSPECIFIED;
llama_pooling_type pooling_type = LLAMA_POOLING_TYPE_UNSPECIFIED; // pooling type for embeddings
enum llama_rope_scaling_type rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_UNSPECIFIED;
enum llama_pooling_type pooling_type = LLAMA_POOLING_TYPE_UNSPECIFIED; // pooling type for embeddings
// // sampling parameters
struct llama_sampling_params sparams;