MCPcopy Create free account
hub / github.com/appdevforall/CodeOnTheGo / llama_decode

Function llama_decode

subprojects/llama.cpp/src/llama-context.cpp:3490–3499  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

3488}
3489
3490int32_t llama_decode(
3491 llama_context * ctx,
3492 llama_batch batch) {
3493 const int ret = ctx->decode(batch);
3494 if (ret != 0 && ret != 1) {
3495 LLAMA_LOG_ERROR("%s: failed to decode, ret = %d\n", __func__, ret);
3496 }
3497
3498 return ret;
3499}
3500
3501//
3502// perf

Callers 15

mainFunction · 0.85
get_hidden_layersFunction · 0.85
mainFunction · 0.85
generate_responseFunction · 0.85
test_promptFunction · 0.85
test_genFunction · 0.85
mainFunction · 0.85

Calls 1

decodeMethod · 0.45

Tested by 9

test_promptFunction · 0.68
test_genFunction · 0.68
decodeMethod · 0.68
decode_tokenMethod · 0.68
decode_tokensMethod · 0.68
test_backend_max_outputsFunction · 0.68
mainFunction · 0.68
mainFunction · 0.68
draftMethod · 0.68