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

batch : auto-gen positions + verify multi-sequence input (#14177)

Browse source 
* batch : verify multi-sequence input batches

ggml-ci

* cont : auto-gen positions + verify multi-seq input

ggml-ci

* cont : first print debug info, then perform validation

ggml-ci

* cont : fix position auto-gen + add comments

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-06-15 09:18:37 +03:00 • committed by GitHub
parent 00ba772610
commit b9912ac570
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 155 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/llama-cparams.h
View file

@ -4,6 +4,7 @@
#include <cstdint>
// TODO: rename to something shorter
#define LLAMA_MAX_PARALLEL_SEQUENCES 64
struct llama_cparams {