vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/nix/sif.nix
#	.github/workflows/build.yml
#	.github/workflows/python-check-requirements.yml
#	README-sycl.md
#	README.md
#	flake.lock
#	flake.nix
#	requirements/requirements-convert-hf-to-gguf.txt
#	scripts/compare-llama-bench.py
This commit is contained in:
Concedo 2024-03-04 15:33:33 +08:00
commit 7c64845dea
41 changed files with 3325 additions and 2053 deletions
Download patch file Download diff file Expand all files Collapse all files

8
common/common.h
View file

@ -70,8 +70,11 @@ struct gpt_params {
float yarn_beta_slow = 1.0f; // YaRN high correction dim
int32_t yarn_orig_ctx = 0; // YaRN original context length
float defrag_thold = -1.0f; // KV cache defragmentation threshold
int32_t rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_UNSPECIFIED;
ggml_numa_strategy numa = GGML_NUMA_STRATEGY_DISABLED;
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
// sampling parameters
int32_t top_k = 40; // <= 0 to use vocab size
@ -129,7 +132,6 @@ struct gpt_params {
bool kl_divergence = false; // compute KL-divergence
bool mul_mat_q = true; // if true, use mul_mat_q kernels instead of cuBLAS
bool random_prompt = false; // do not randomize prompt if none provided
bool use_color = false; // use color to distinguish generations and inputs
bool interactive = false; // interactive mode