8fac4b1cc8
EAGLE3 is an encoder-decoder based speculative decoding method: - Extracts features from target model at specific layers - Uses feature fusion layer to compress target features - Generates draft tokens with single-layer decoder - Maps draft vocabulary to target vocabulary via d2t tensor Key changes: - Add LLM_ARCH_EAGLE3 architecture - Add EAGLE3 encoder/decoder graph (src/models/eagle3.cpp) - Add feature extraction from target model layers - Add g_embeddings handling for decoder input - Add GGML_TENSOR_FLAG_SYNC for GPU synchronization - Add --eagle3 flag for speculative-simple example - Add EAGLE3 model conversion in convert_hf_to_gguf.py |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| README.md | ||
| speculative-simple.cpp | ||
README.md
llama.cpp/examples/speculative-simple
Demonstration of basic greedy speculative decoding
./bin/llama-speculative-simple \
-m ../models/qwen2.5-32b-coder-instruct/ggml-model-q8_0.gguf \
-md ../models/qwen2.5-1.5b-coder-instruct/ggml-model-q4_0.gguf \
-f test.txt -c 0 -ngl 99 --color \
--sampling-seq k --top-k 1 -fa --temp 0.0 \
-ngld 99 --draft-max 16 --draft-min 5 --draft-p-min 0.9