Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	docs/backend/CANN.md
#	examples/model-conversion/Makefile
#	examples/model-conversion/scripts/causal/compare-embeddings-logits.sh
#	examples/model-conversion/scripts/causal/convert-model.sh
#	examples/model-conversion/scripts/causal/run-casual-gen-embeddings-org.py
#	examples/model-conversion/scripts/causal/run-converted-model-embeddings-logits.sh
#	examples/model-conversion/scripts/causal/run-converted-model.sh
#	examples/model-conversion/scripts/embedding/compare-embeddings-logits.sh
#	examples/model-conversion/scripts/embedding/convert-model.sh
#	examples/model-conversion/scripts/embedding/modelcard.template
#	examples/model-conversion/scripts/embedding/run-converted-model.sh
#	examples/model-conversion/scripts/utils/create-collection-add-model.sh
#	examples/model-conversion/scripts/utils/inspect-converted-model.sh
#	examples/model-conversion/scripts/utils/inspect-org-model.py
#	examples/model-conversion/scripts/utils/perplexity-gen.sh
#	examples/model-conversion/scripts/utils/perplexity-run-simple.sh
#	examples/model-conversion/scripts/utils/perplexity-run.sh
#	examples/model-conversion/scripts/utils/quantize.sh
#	examples/model-conversion/scripts/utils/run-embedding-server.sh
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	src/llama-context.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
This commit is contained in:
Concedo
2025-09-05 13:25:34 +08:00
parent 979e2113e2 5d6688de08
commit f0d4128e9f
43 changed files with 1408 additions and 256 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
+2 -25
View File
@@ -27,11 +27,10 @@ llama_kv_cache::llama_kv_cache(
uint32_t n_seq_max,
uint32_t n_pad,
uint32_t n_swa,
llama_swa_type swa_type,
const layer_filter_cb & filter,
const layer_reuse_cb & reuse) :
model(model), hparams(model.hparams), v_trans(v_trans),
n_seq_max(n_seq_max), n_stream(unified ? 1 : n_seq_max), n_pad(n_pad), n_swa(n_swa), swa_type(swa_type) {
n_seq_max(n_seq_max), n_stream(unified ? 1 : n_seq_max), n_pad(n_pad), n_swa(n_swa) {
GGML_ASSERT(kv_size % n_pad == 0);
@@ -1393,29 +1392,7 @@ ggml_cgraph * llama_kv_cache::build_graph_shift(llm_graph_result * res, llama_co
}
bool llama_kv_cache::is_masked_swa(llama_pos p0, llama_pos p1) const {
assert(p0 >= 0 && p1 >= 0);
switch (swa_type) {
case LLAMA_SWA_TYPE_NONE:
{
} break;
case LLAMA_SWA_TYPE_STANDARD:
{
if (p1 - p0 >= (int32_t) n_swa) {
return true;
}
} break;
case LLAMA_SWA_TYPE_CHUNKED:
{
const llama_pos pos_chunk_start = (p1 / n_swa) * n_swa;
if (p0 < pos_chunk_start) {
return true;
}
} break;
}
return false;
return hparams.is_masked_swa(p0, p1);
}
void llama_kv_cache::state_write(llama_io_write_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) const {