vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 17:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit '8f47e25f56' into concedo_experimental

Browse source 
# Conflicts:
#	.github/labeler.yml
#	.github/workflows/build-linux-cross.yml
#	docs/backend/CANN.md
#	examples/batched.swift/Sources/main.swift
#	examples/embedding/embedding.cpp
#	examples/gritlm/gritlm.cpp
#	examples/llama.android/llama/src/main/cpp/llama-android.cpp
#	examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	examples/passkey/passkey.cpp
#	examples/retrieval/retrieval.cpp
#	examples/save-load-state/save-load-state.cpp
#	examples/simple-chat/simple-chat.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	tools/batched-bench/batched-bench.cpp
#	tools/cvector-generator/cvector-generator.cpp
#	tools/imatrix/imatrix.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/perplexity/perplexity.cpp
#	tools/run/run.cpp
This commit is contained in:
Concedo 2025-06-13 22:05:03 +08:00
commit 4204f111f7
24 changed files with 204 additions and 91 deletions
Download patch file Download diff file Expand all files Collapse all files

14
tools/main/main.cpp
View file

@ -148,6 +148,8 @@ int main(int argc, char ** argv) {
return 1;
}
auto * mem = llama_get_memory(ctx);
const llama_vocab * vocab = llama_model_get_vocab(model);
auto chat_templates = common_chat_templates_init(model, params.chat_template);
@ -352,7 +354,7 @@ int main(int argc, char ** argv) {
}
// remove any "future" tokens that we might have inherited from the previous session
llama_kv_self_seq_rm(ctx, -1, n_matching_session_tokens, -1);
llama_memory_seq_rm(mem, -1, n_matching_session_tokens, -1);
}
LOG_DBG("recalculate the cached logits (check): embd_inp.size() %zu, n_matching_session_tokens %zu, embd_inp.size() %zu, session_tokens.size() %zu\n",
@ -600,8 +602,8 @@ int main(int argc, char ** argv) {
LOG_DBG("context full, swapping: n_past = %d, n_left = %d, n_ctx = %d, n_keep = %d, n_discard = %d\n",
n_past, n_left, n_ctx, params.n_keep, n_discard);
llama_kv_self_seq_rm (ctx, 0, params.n_keep , params.n_keep + n_discard);
llama_kv_self_seq_add(ctx, 0, params.n_keep + n_discard, n_past, -n_discard);
llama_memory_seq_rm (mem, 0, params.n_keep , params.n_keep + n_discard);
llama_memory_seq_add(mem, 0, params.n_keep + n_discard, n_past, -n_discard);
n_past -= n_discard;
@ -624,9 +626,9 @@ int main(int argc, char ** argv) {
LOG_DBG("div: [%6d, %6d] / %6d -> [%6d, %6d]\n", ga_i + ib*bd, ga_i + ib*bd + ga_w, ga_n, (ga_i + ib*bd)/ga_n, (ga_i + ib*bd + ga_w)/ga_n);
LOG_DBG("shift: [%6d, %6d] + %6d -> [%6d, %6d]\n", ga_i + ib*bd + ga_w, n_past + ib*bd, dd, ga_i + ib*bd + ga_w + dd, n_past + ib*bd + dd);
llama_kv_self_seq_add(ctx, 0, ga_i, n_past, ib*bd);
llama_kv_self_seq_div(ctx, 0, ga_i + ib*bd, ga_i + ib*bd + ga_w, ga_n);
llama_kv_self_seq_add(ctx, 0, ga_i + ib*bd + ga_w, n_past + ib*bd, dd);
llama_memory_seq_add(mem, 0, ga_i, n_past, ib*bd);
llama_memory_seq_div(mem, 0, ga_i + ib*bd, ga_i + ib*bd + ga_w, ga_n);
llama_memory_seq_add(mem, 0, ga_i + ib*bd + ga_w, n_past + ib*bd, dd);
n_past -= bd;