Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-27 21:46:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

llama: add llama_batch_ext (#24669)

Browse Source 
* (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
This commit is contained in:
Xuan-Son Nguyen
2026-09-24 16:25:07 +02:00
committed by GitHub
parent 308883b335
commit fc343a84bb
10 changed files with 1210 additions and 262 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama-cpp.h
+5
View File
@@ -24,7 +24,12 @@ struct llama_adapter_lora_deleter {
void operator()(llama_adapter_lora * adapter) { llama_adapter_lora_free(adapter); }
};
struct llama_batch_ext_deleter {
void operator()(llama_batch_ext * batch) { llama_batch_ext_free(batch); }
};
typedef std::unique_ptr<llama_model, llama_model_deleter> llama_model_ptr;
typedef std::unique_ptr<llama_context, llama_context_deleter> llama_context_ptr;
typedef std::unique_ptr<llama_sampler, llama_sampler_deleter> llama_sampler_ptr;
typedef std::unique_ptr<llama_adapter_lora, llama_adapter_lora_deleter> llama_adapter_lora_ptr;
typedef std::unique_ptr<llama_batch_ext, llama_batch_ext_deleter> llama_batch_ext_ptr;