summaryrefslogtreecommitdiff
path: root/examples/speculative/speculative.cpp
diff options
context:
space:
mode:
authorGeorgi Gerganov <ggerganov@gmail.com>2024-03-04 22:31:20 +0200
committerGitHub <noreply@github.com>2024-03-04 22:31:20 +0200
commit29ae62d2ae163e2b68aa0ad3bf2ab4636de0c957 (patch)
treea65058dfddf1672f1d765e324dac9f66abf1a7c1 /examples/speculative/speculative.cpp
parente0843afe1b37890b631bc7d3d2da2ed36c862b91 (diff)
llama : fix embeddings (#5796)
* llama : fix embeddings ggml-ci * llama : do not use KV cache for non-causal models ggml-ci * embeddings : fix llama_batch_init arg * llama : add pooling switch * llama : distinguish token vs sequence embeddings ggml-ci * llama : assert pooling tensor * llama : simplify causal mask condition ggml-ci * llama : assert input batch with pooling enabled * readme : update API changes list
Diffstat (limited to 'examples/speculative/speculative.cpp')
0 files changed, 0 insertions, 0 deletions