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
This commit is contained in:
@@ -315,7 +315,7 @@ llama_tokens common_speculative_gen_draft(
|
||||
for (int i = 0; i < params.n_draft; ++i) {
|
||||
common_batch_clear(batch);
|
||||
|
||||
common_sampler_sample(smpl, ctx_dft, 0, true);
|
||||
common_sampler_sample(smpl, ctx_dft, 0);
|
||||
|
||||
const auto * cur_p = common_sampler_get_candidates(smpl, true);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user