happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/examples/parallel
History
Georgi Gerganov 254098a279
common : refactor common_sampler + grammar logic changes (#17937) 
* common : refactor common_sampler + grammar logic changes

* tests : increase max_tokens to get needed response

* batched : fix uninitialized samplers
 		2025-12-14 10:11:13 +02:00
..
CMakeLists.txt ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
README.md parallel : increase the variability of the prompt lengths (#13927) 2025-05-30 19:38:07 +03:00
parallel.cpp common : refactor common_sampler + grammar logic changes (#17937) 2025-12-14 10:11:13 +02:00

README.md

llama.cpp/example/parallel

Simplified simulation of serving incoming requests in parallel

Example

Generate 128 client requests (-ns 128), simulating 8 concurrent clients (-np 8). The system prompt is shared (-pps), meaning that it is computed once at the start. The client requests consist of up to 10 junk questions (--junk 10) followed by the actual question.

llama-parallel -m model.gguf -np 8 -ns 128 --top-k 1 -pps --junk 10 -c 16384

[!NOTE] It's recommended to use base models with this example. Instruction tuned models might not be able to properly follow the custom chat template specified here, so the results might not be as expected.