Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests 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
tests/test-arg-parser.cpp
+30
View File
@@ -2,7 +2,9 @@
#include "common.h"
#include "download.h"
#include "llama.h"
#include "speculative.h"
#include <limits>
#include <string>
#include <vector>
#include <sstream>
@@ -14,6 +16,34 @@
static void test(void) {
common_params params;
auto assert_output_limits = [](int32_t n_batch, int32_t n_parallel, int32_t n_draft,
int32_t total, int32_t per_seq) {
const auto limits = common_speculative_get_output_limits(n_batch, n_parallel, n_draft);
assert(limits.total == total);
assert(limits.per_seq == per_seq);
};
assert_output_limits(16, 2, 3, 8, 4);
assert_output_limits(16, 2, -1, 2, 1);
assert_output_limits( 6, 2, 3, 6, 4);
assert_output_limits( 2, 1, 3, 2, 2);
assert_output_limits(
std::numeric_limits<int32_t>::max(),
std::numeric_limits<int32_t>::max(),
std::numeric_limits<int32_t>::max(),
std::numeric_limits<int32_t>::max(),
std::numeric_limits<int32_t>::max());
{
common_params base;
base.n_parallel = 4;
base.n_outputs_max_per_seq = 8;
const auto draft = common_base_params_to_speculative(base);
assert(draft.n_outputs_max == 4);
assert(draft.n_outputs_max_per_seq == 1);
}
printf("test-arg-parser: make sure there is no duplicated arguments in any examples\n\n");
for (int ex = 0; ex < LLAMA_EXAMPLE_COUNT; ex++) {
try {