public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-21 09:41:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-12 19:23:56 +03:00
parent 6d64e4abf3
commit 6ddff4d96a
24 changed files with 2831 additions and 690 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-batch.h
+8 -1
View File
@@ -54,6 +54,7 @@ public:
uint32_t get_n_tokens() const;
uint32_t get_n_outputs() const;
uint32_t get_n_used() const;
// the array of output indices in the order they were encountered during the ubatch splitting
std::vector<int32_t> & get_out_ids();
@@ -69,7 +70,8 @@ public:
llama_ubatch split_simple(uint32_t n_ubatch);
// make ubatches of equal-length sequences sets
llama_ubatch split_equal(uint32_t n_ubatch);
// if sequential == true, the tokens in the ubatch will have increasing sequential sequence ids
llama_ubatch split_equal(uint32_t n_ubatch, bool sequential);
// sequence-set-wise split - each ubatch contains a single sequence-set
llama_ubatch split_seq(uint32_t n_ubatch);
@@ -112,6 +114,9 @@ private:
using pos_set_t = std::set<llama_pos>;
using seq_cpl_t = std::vector<bool>;
// helper flag to quickly determine if there are any coupled sequences in the batch
bool has_cpl;
std::vector<pos_set_t> seq_pos; // seq_pos[s]: the set of positions in sequence s
std::vector<seq_cpl_t> seq_cpl; // seq_cpl[s0][s1]: if sequence s0 is coupled to sequence s1
@@ -125,6 +130,8 @@ private:
// batch indices of the output
std::vector<int32_t> out_ids;
uint32_t n_used;
// used[i] indicates if token i has already been used in a previous ubatch
std::vector<bool> used;