mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-13 18:29:12 +02:00

Files

T

Georgi Gerganov bc21975084 speculative : fix handling of some input params (#9963 )

* speculative : fix batch sizes at initialization

ggml-ci

* speculative : handle params.n_predict == -1

* speculative : limit batch size to llama_n_batch

2024-10-21 09:37:12 +03:00

CMakeLists.txt

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809 )

2024-06-13 00:41:52 +01:00

README.md

speculative : implement stochastic speculative sampling (#5625 )

2024-03-04 20:24:00 +02:00

speculative.cpp

speculative : fix handling of some input params (#9963 )

2024-10-21 09:37:12 +03:00

README.md

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info:

https://github.com/ggerganov/llama.cpp/pull/2926
https://github.com/ggerganov/llama.cpp/pull/3624
https://github.com/ggerganov/llama.cpp/pull/5625