0 0 0 C++

llama : refactor sampling v2 (#9294)

- Add `struct llama_sampler` and `struct llama_sampler_i`
- Add `llama_sampler_` API
- Add `llama_sampler_chain_` API for chaining multiple samplers
- Remove `LLAMA_API_INTERNAL`
- Add `llama_perf_` API and remove old `llama_print_timings` and `llama_reset_timings`

Georgi Gerganov committed 2y ago

df270ef74596da8f1178f08991f4c51f18c9ee82

Parent: 947538a

Committed by GitHub <noreply@github.com> on 9/7/2024, 12:16:19 PM