ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : refactor k-shift implementation + KV defragmentation (#5691)

Browse source 
* llama : refactor k-shift implementation

ggml-ci

* llama : rename llama_kv_cache_seq_shift to llama_kv_cache_seq_add

* llama : cont k-shift refactoring + normalize type names

ggml-ci

* minor : fix MPI builds

* llama : reuse n_rot from the build context

ggml-ci

* llama : revert enum name changes from this PR

ggml-ci

* llama : update llama_rope_type

* llama : add comment about rope values

* llama : fix build

* passkey : apply kv cache updates explicitly

ggml-ci

* llama : change name to llama_kv_cache_update()

* llama : add llama_kv_cache_seq_pos_max()

* passkey : fix llama_kv_cache_seq_pos_max() usage

* llama : some llama_kv_cell simplifications

* llama : add llama_kv_cache_compress (EXPERIMENTAL)

* llama : add alternative KV cache merging (EXPERIMENTAL)

* llama : add llama_kv_cache_defrag

* llama : comments

* llama : remove llama_kv_cache_compress

will add in a separate PR

ggml-ci

* llama : defragment via non-overlapping moves

* llama : ggml_graph based defrag implementation

ggml-ci

* llama : switch the loop order in build_defrag

* llama : add comments
This commit is contained in:
Georgi Gerganov 2024-02-25 22:12:24 +02:00 • committed by GitHub
parent f7625019c5
commit bf08e00643
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 646 additions and 304 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/server/server.cpp
View file

@ -1636,8 +1636,8 @@ struct llama_server_context
{"n_system_tokens", system_tokens.size()},
{"n_cache_tokens", slot.cache_tokens.size()}
});
llama_kv_cache_seq_rm (ctx, slot.id, n_keep , n_keep + n_discard);
llama_kv_cache_seq_shift(ctx, slot.id, n_keep + n_discard, system_tokens.size() + slot.n_past, -n_discard);
llama_kv_cache_seq_rm (ctx, slot.id, n_keep , n_keep + n_discard);
llama_kv_cache_seq_add(ctx, slot.id, n_keep + n_discard, system_tokens.size() + slot.n_past, -n_discard);
for (size_t i = n_keep + n_discard; i < slot.cache_tokens.size(); i++)
{
@ -1941,9 +1941,9 @@ struct llama_server_context
LOG_TEE("div: [%6d, %6d] / %6d -> [%6d, %6d]\n", slot.ga_i + ib * bd, slot.ga_i + ib * bd + slot.ga_w, slot.ga_n, (slot.ga_i + ib * bd) / slot.ga_n, (slot.ga_i + ib * bd + slot.ga_w) / slot.ga_n);
LOG_TEE("shift: [%6d, %6d] + %6d -> [%6d, %6d]\n", slot.ga_i + ib * bd + slot.ga_w, slot.n_past_se + ib * bd, dd, slot.ga_i + ib * bd + slot.ga_w + dd, slot.n_past_se + ib * bd + dd);
llama_kv_cache_seq_shift(ctx, slot.id, slot.ga_i, slot.n_past_se, ib * bd);
llama_kv_cache_seq_add(ctx, slot.id, slot.ga_i, slot.n_past_se, ib * bd);
llama_kv_cache_seq_div(ctx, slot.id, slot.ga_i + ib * bd, slot.ga_i + ib * bd + slot.ga_w,slot.ga_n);
llama_kv_cache_seq_shift(ctx, slot.id, slot.ga_i + ib * bd + slot.ga_w,slot.n_past_se + ib * bd, dd);
llama_kv_cache_seq_add(ctx, slot.id, slot.ga_i + ib * bd + slot.ga_w,slot.n_past_se + ib * bd, dd);
slot.n_past_se -= bd;