vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-rocm.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/python-type-check.yml
#	CMakeLists.txt
#	CONTRIBUTING.md
#	README.md
#	ci/run.sh
#	examples/embedding/embedding.cpp
#	examples/server/README.md
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/ggml.c
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/sync-ggml.last
#	src/llama-vocab.cpp
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-tokenizer-0.cpp
This commit is contained in:
Concedo 2024-10-02 01:00:57 +08:00
commit ce7f9c9a2c
39 changed files with 103400 additions and 102738 deletions
Download patch file Download diff file Expand all files Collapse all files

7
common/common.cpp
View file

@ -1025,6 +1025,11 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
cparams.flash_attn = params.flash_attn;
cparams.no_perf = params.no_perf;
if (params.reranking) {
cparams.embeddings = true;
cparams.pooling_type = LLAMA_POOLING_TYPE_RANK;
}
cparams.type_k = kv_cache_type_from_str(params.cache_type_k);
cparams.type_v = kv_cache_type_from_str(params.cache_type_v);
@ -1434,6 +1439,8 @@ void llama_batch_add(
llama_pos pos,
const std::vector<llama_seq_id> & seq_ids,
bool logits) {
GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded");
batch.token [batch.n_tokens] = id;
batch.pos [batch.n_tokens] = pos;
batch.n_seq_id[batch.n_tokens] = seq_ids.size();