thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

model, mtmd: fix gguf conversion for audio/vision mmproj (#21309)

Browse source 
* fix gguf conversion for audio/vision mmproj

* fix test
This commit is contained in:
Xuan-Son Nguyen 2026-04-02 17:10:32 +02:00 • committed by GitHub
parent 223373742b
commit 63f8fe0ef4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
27 changed files with 1462 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

7
examples/eval-callback/eval-callback.cpp
View file

@ -15,13 +15,18 @@ static bool run(llama_context * ctx, const common_params & params) {
const bool add_bos = llama_vocab_get_add_bos(vocab);
std::vector<llama_token> tokens = common_tokenize(ctx, params.prompt, add_bos);
std::vector<llama_token> tokens = common_tokenize(ctx, params.prompt, add_bos, true);
if (tokens.empty()) {
LOG_ERR("%s : there are not input tokens to process - (try to provide a prompt with '-p')\n", __func__);
return false;
}
LOG_INF("number of input tokens = %zu\n", tokens.size());
for (size_t i = 0; i < tokens.size(); ++i) {
LOG_INF(" %d\n", tokens[i]);
}
if (llama_decode(ctx, llama_batch_get_one(tokens.data(), tokens.size()))) {
LOG_ERR("%s : failed to eval\n", __func__);
return false;