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

llama : allow exporting a view of the KV cache (#4180)

Browse source 
* Allow exporting a view of the KV cache

* Allow dumping the sequences per cell in common

* Track max contiguous cells value and position as well

* Fix max contiguous empty cells index calculation

Make dump functions deal with lengths or sequences counts > 10 better

* Fix off by one error in dump_kv_cache_view

* Add doc comments for KV cache view functions

Eliminate cell sequence struct; use llama_seq_id directly

Minor cleanups
This commit is contained in:
Kerfuffle 2023-11-23 09:31:20 -07:00 • committed by GitHub
parent 671f639c59
commit 5df7d06c42
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 227 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
common/common.h
View file

@ -218,3 +218,13 @@ std::string get_sortable_timestamp();
void dump_non_result_info_yaml(
FILE * stream, const gpt_params & params, const llama_context * lctx,
const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc);
//
// KV cache utils
//
// Dump the KV cache view with the number of sequences per cell.
void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80);
// Dump the KV cache view showing individual sequences in each cell (long output).
void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);