upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-05 09:30:49 -05:00
Code Issues Packages Projects Releases Wiki Activity

MTP: clean-up (#9)

Browse Source 
* MTP: clean-up

* review: use llama_context_type instead of llama_graph_type

* review: remove llama_model_has_mtp

* review: fix convert issues

* convert: fix pycheck

* review: formatting

* use `mtp-` for identifying mtp models

* convert: fix mtp conversion
This commit is contained in:
Aman Gupta
2026-05-13 11:12:20 +08:00
parent 5c58cc5bdd
commit 3c3aebaaa0
20 changed files with 687 additions and 646 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/llama.h
View File

@@ -198,6 +198,11 @@ extern "C" {
LLAMA_SPLIT_MODE_TENSOR = 3,
};
enum llama_context_type {
LLAMA_CONTEXT_TYPE_DEFAULT = 0,
LLAMA_CONTEXT_TYPE_MTP = 1,
};
// TODO: simplify (https://github.com/ggml-org/llama.cpp/pull/9294#pullrequestreview-2286561979)
typedef struct llama_token_data {
llama_token id; // token id
@@ -339,6 +344,7 @@ extern "C" {
int32_t n_threads; // number of threads to use for generation
int32_t n_threads_batch; // number of threads to use for batch processing
enum llama_context_type ctx_type; // set the context type (e.g. MTP)
enum llama_rope_scaling_type rope_scaling_type; // RoPE scaling type, from `enum llama_rope_scaling_type`
enum llama_pooling_type pooling_type; // whether to pool (sum) embedding results by sequence id
enum llama_attention_type attention_type; // attention type to use for embeddings