upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-26 16:07:32 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,163 Commits 812 Branches 7,611 Tags
b11163
Commit Graph
2 Commits
Author SHA1 Message Date
Xuan-Son Nguyen fc343a84bb llama: add llama_batch_ext (#24669) 
* (wip) add llama_batch_ext

* wip

* updated design

* updated impl

* change signature

* unused var

* demo common_prompt_batch_decode

* fix pos

* tmp disable test-batch-alloc

* fix compat

* nits: add const

* no more pos_max

* add comment about llama_batch_ext_set_embd_state

* handle n_embd_out properly

* rename api --> embd_token

* llama_embd

* stub llama_batch_ext_set_embd_state

* support both token + embd + state in batch

* llama_batch_ext_add_embd

* upstream some changes

* nits

* fix test-batch-alloc

* add test for compat
 2026-09-24 16:25:07 +02:00
Aman Gupta 961e4b26a7 llama-batch: add unit test (#25471) 
* llama-batch: add unit test

* fix win32 builds

* add not implemented assertion in unused methods

* remove unreachable code
 2026-07-10 11:04:31 +08:00