diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2023-10-18 16:21:57 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-10-18 16:21:57 +0300 |
| commit | 0e89203b517c95ec6675eda75d200a60d1e8921d (patch) | |
| tree | 3aba40ef0362d061f240bd43c52e86a8f728f89d /examples/llava/llava-utils.h | |
| parent | c67fe68e417f766970fb1feaf2e66458aa24116a (diff) | |
speculative : add tree-based sampling example (#3624)
* sampling : one sequence per sampling context
ggml-ci
* speculative : add tree-based sampling support
ggml-ci
* speculative : reuse the n_parallel CLI param
* speculative : refactor sampling
* examples : fix build after sampling refactoring
ggml-ci
* batched : fix n_seq_id
* sampling : fix malloc
ggml-ci
* swift : fix build
ggml-ci
* swift : try to fix build
ggml-ci
* prompts : add assistant.txt
* common : add llama_batch_add() and llama_batch_clear() helpers
* speculative : minor refactor
ggml-ci
* minor : comments + rename
ggml-ci
* speculative : fix off-by-one for n_drafted
* speculative : fix the n_drafted fix + p constants
Diffstat (limited to 'examples/llava/llava-utils.h')
| -rw-r--r-- | examples/llava/llava-utils.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/llava/llava-utils.h b/examples/llava/llava-utils.h index 4e71351d..e050b59b 100644 --- a/examples/llava/llava-utils.h +++ b/examples/llava/llava-utils.h @@ -17,7 +17,7 @@ inline bool eval_image_embd(llama_context * ctx_llama, float * embd, int N, int if (n_eval > n_batch) { n_eval = n_batch; } - llama_batch batch = {int32_t(n_eval), nullptr, (embd+i*n_embd), nullptr, nullptr, nullptr, *n_past, 1, 0, }; + llama_batch batch = {int32_t(n_eval), nullptr, (embd+i*n_embd), nullptr, nullptr, nullptr, nullptr, *n_past, 1, 0, }; if (llama_decode(ctx_llama, batch)) { fprintf(stderr, "%s : failed to eval\n", __func__); return false; |