wylab/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-06 17:57:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

llama : support multi-output backend sampling (#25532)

Browse Source 
* Enable backend sampling with token speculation

* Clamp the mask sum before converting it into the sampled index

* Add a numeric context parameter declaring the maximum outputs one sequence

* More fixes

* Don't reuse memory for output views.

* Match dist between CPU and GPU

* Fix CPU and backend sampling mismatches

* Simpify some of the changes

* Fix tests on Vulkan

* More test fixes

* Rebase changes

* Rebase and address review comments

* Address review comments

* Address review comments

* Update src/llama-sampler.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Gaurav Garg
2026-08-10 16:58:56 +03:00
committed by GitHub
co-authored by Georgi Gerganov
parent d2f83055d6
commit dd1ea52433
24 changed files with 1305 additions and 391 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/speculative.cpp
+12
View File
@@ -2299,6 +2299,7 @@ common_params common_base_params_to_speculative(const common_params & params) {
result.cache_type_k = params_spec.cache_type_k;
result.cache_type_v = params_spec.cache_type_v;
result.n_outputs_max = params.n_parallel;
result.n_outputs_max_per_seq = 1;
return result;
}
@@ -2384,6 +2385,17 @@ common_speculative_init_result_ptr common_speculative_init_from_params(common_pa
return std::make_unique<common_speculative_init_result>(params, model_tgt, ctx_tgt);
}
common_speculative_output_limits common_speculative_get_output_limits(
int32_t n_batch, int32_t n_parallel, int32_t n_draft) {
const int64_t per_seq = 1 + (int64_t) std::max(0, n_draft);
const int64_t total = (int64_t) n_parallel * per_seq;
return {
/* .total = */ (int32_t) std::min<int64_t>(n_batch, total),
/* .per_seq = */ (int32_t) std::min<int64_t>(n_batch, per_seq),
};
}
// initialization of the speculative decoding system
//
common_speculative * common_speculative_init(common_params_speculative & params, uint32_t n_seq) {