ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231)

* ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer

* ggml : remove scale parameters from lightning indexer OP, add f16 mask parameter

* tests : add GGML_OP_LIGHTNING_INDEXER tests

* ggml : bump RPC version

* chore : check if lightning indexer input tensors are not transposed

* tests : count flops instead of bandwidth in lightning indexer test

* chore : add missing const

* chore : whitespace

* ggml : renamed variables in CPU lightning indexer implementation

* ggml : fix lightning indexer mask broadcasting

* tests : tests for lightning indexer mask broadcasting

* chore : whitespace

* llama : use GGML_OP_LIGHTNING_INDEXER in DeepSeek V3.2 and DeepSeek V4 models

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
fairydreaming
2026-07-11 11:39:07 +02:00
committed by GitHub
co-authored by Stanisław Szymczyk
parent 76f2798059
commit 00f5442cc4
13 changed files with 324 additions and 52 deletions
+2 -2
View File
@@ -8,10 +8,10 @@ extern "C" {
#define RPC_PROTO_MAJOR_VERSION 4
#define RPC_PROTO_MINOR_VERSION 0
#define RPC_PROTO_PATCH_VERSION 1
#define RPC_PROTO_PATCH_VERSION 2
#ifdef __cplusplus
static_assert(GGML_OP_COUNT == 97, "GGML_OP_COUNT has changed - update RPC_PROTO_PATCH_VERSION");
static_assert(GGML_OP_COUNT == 98, "GGML_OP_COUNT has changed - update RPC_PROTO_PATCH_VERSION");
#endif
#define GGML_RPC_MAX_SERVERS 16