vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-07 17:22:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

test-backend-ops: allow loading tests from file and parsing model operators into file (#19896)

Browse source 
* tests: allow loading test-backend-ops tests from json

* add error threshold based on op

* add error when file cannot be read

* add graph operator json extraction tool

* add nb parameter for non-contiguous input tensors

* fix view check

* only use view if non-contiguous/permuted, use C++ random instead of rand()

* replace internal API calls with public llama_graph_reserve call

* reduce test description length

* fix nb[0] not getting set for view

* add name to tests

* fix inplace error

* use text file instead of json

* move llama_graph_reserve function to new llama-ext header, move export-graph-ops to tests/

* fix missing declaration

* use pragma once

* fix indent

* fix Windows build
This commit is contained in:
Ruben Ortlam 2026-03-12 13:26:00 +01:00 • committed by GitHub
parent 6de1bc631d
commit 128142fe7d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 529 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

14
src/llama-context.cpp
View file

@ -7,6 +7,7 @@
#include "llama-memory.h"
#include "llama-mmap.h"
#include "llama-model.h"
#include "llama-ext.h"
#include <cinttypes>
#include <cmath>
@ -3129,6 +3130,19 @@ uint32_t llama_get_sampled_probs_count_ith(llama_context * ctx, int32_t i) {
return static_cast<uint32_t>(ctx->get_sampled_probs_count(i));
}
struct ggml_cgraph * llama_graph_reserve(
struct llama_context * ctx,
uint32_t n_tokens,
uint32_t n_seqs,
uint32_t n_outputs) {
auto * memory = ctx->get_memory();
llama_memory_context_ptr mctx;
if (memory) {
mctx = memory->init_full();
}
return ctx->graph_reserve(n_tokens, n_seqs, n_outputs, mctx.get());
}
// llama adapter API
int32_t llama_set_adapters_lora(