tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-27 18:49:40 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : reuse compute graphs (#14482)

Browse Source 
* llama : reuse compute graphs

ggml-ci

* llama-bench : add graph reuse parameter

ggml-ci

* cont : remove the parameter and the sched resets

ggml-ci

* graph : rename update() to can_reuse()

ggml-ci

* params : remove is_same()

ggml-ci

* graph : set res->params in llm_graph_context constructor

ggml-ci

* graph : avoid set_max_nodes in llm_graph_result

ggml-ci

* kv-cache : reuse llama_context's graph result instance

ggml-ci

* context : reset the previous graph result upon memory updates

ggml-ci

* batch : llama_ubatch now carries its data instead of pointing to balloc

ggml-ci

* merge : fix build

ggml-ci

* graph : fix can_reuse() checks when flash-attention is disabled

* graph : move llm_graph_result impl in source file + debug env

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-17 19:08:33 +03:00
committed by GitHub
parent 086cf81e88
commit 01612b7409
12 changed files with 548 additions and 289 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/llama-kv-cache-unified.h
View File

@@ -154,6 +154,9 @@ public:
uint32_t get_n_kv() const;
// TODO: temporary
bool get_supports_set_rows() const;
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const;
ggml_tensor * get_v(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const;
@@ -227,7 +230,7 @@ private:
// env: LLAMA_SET_ROWS (temporary)
// ref: https://github.com/ggml-org/llama.cpp/pull/14285
int supports_set_rows = false;
bool supports_set_rows = false;
const llama_swa_type swa_type = LLAMA_SWA_TYPE_NONE;
@@ -270,15 +273,13 @@ private:
float freq_base,
float freq_scale) const;
llm_graph_result_ptr build_graph_shift(
const llama_cparams & cparams,
ggml_context * ctx,
ggml_cgraph * gf) const;
ggml_cgraph * build_graph_shift(
llm_graph_result * res,
llama_context * lctx) const;
llm_graph_result_ptr build_graph_defrag(
const llama_cparams & cparams,
ggml_context * ctx,
ggml_cgraph * gf,
ggml_cgraph * build_graph_defrag(
llm_graph_result * res,
llama_context * lctx,
const defrag_info & dinfo) const;
struct cell_ranges_t {
@@ -340,6 +341,9 @@ public:
uint32_t get_n_kv() const;
// TODO: temporary
bool get_supports_set_rows() const;
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il) const;
ggml_tensor * get_v(ggml_context * ctx, int32_t il) const;