diff options
| author | LeonEricsson <70749762+LeonEricsson@users.noreply.github.com> | 2023-12-22 17:05:56 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-12-22 18:05:56 +0200 |
| commit | 7082d24cec35e9ce9147535a2224dfc67ee0a78c (patch) | |
| tree | b87d0e65d71c8e2a5bdb889483c75d4429d2d566 /common/common.h | |
| parent | ba661751322a7c201fd3bef71af077c5aebfaa2a (diff) | |
lookup : add prompt lookup decoding example (#4484)
* initial commit, going through initializations
* main loop finished, starting to debug
* BUG: generates gibberish/repeating tokens after a while
* kv_cache management
* Added colors to distinguish drafted tokens (--color). Updated README
* lookup : fix token positions in the draft batch
* lookup : use n_draft from CLI params
* lookup : final touches
---------
Co-authored-by: Leon Ericsson <leon.ericsson@icloud.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'common/common.h')
| -rw-r--r-- | common/common.h | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/common/common.h b/common/common.h index e87ce113..9659aa04 100644 --- a/common/common.h +++ b/common/common.h @@ -51,7 +51,7 @@ struct gpt_params { int32_t n_ctx = 512; // context size int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS) int32_t n_keep = 0; // number of tokens to keep from initial prompt - int32_t n_draft = 16; // number of tokens to draft during speculative decoding + int32_t n_draft = 8; // number of tokens to draft during speculative decoding int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited) int32_t n_parallel = 1; // number of parallel sequences to decode int32_t n_sequences = 1; // number of sequences to decode @@ -240,3 +240,4 @@ 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); + |