starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-18 14:54:11 +02:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Update vendored llama.cpp to b7847" (#14061)

Browse Source
This commit is contained in:
Jeffrey Morgan
2026-02-03 18:39:36 -08:00
committed by GitHub
parent a6355329bf
commit b1fccabb34
240 changed files with 5050 additions and 21247 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
llama/llama.cpp/common/sampling.h vendored
View File

@@ -36,8 +36,7 @@ struct common_sampler;
// llama_sampler API overloads
// note: can mutate params in some cases
struct common_sampler * common_sampler_init(const struct llama_model * model, struct common_params_sampling & params);
struct common_sampler * common_sampler_init(const struct llama_model * model, const struct common_params_sampling & params);
void common_sampler_free(struct common_sampler * gsmpl);
@@ -49,7 +48,6 @@ struct common_sampler * common_sampler_clone (struct common_sampler * gsmpl);
// arguments can be nullptr to skip printing
void common_perf_print(const struct llama_context * ctx, const struct common_sampler * gsmpl);
// get the underlying llama_sampler_chain
struct llama_sampler * common_sampler_get(const struct common_sampler * gsmpl);
// extended sampling implementation:
@@ -59,10 +57,7 @@ struct llama_sampler * common_sampler_get(const struct common_sampler * gsmpl);
// - check if the token fits the grammar (if any)
// - if not: resample by first applying the grammar constraints and then sampling again (slower path)
//
// if grammar_first is true, the grammar is applied before the samplers (slower)
// useful in cases where all the resulting candidates (not just the sampled one) must fit the grammar
//
llama_token common_sampler_sample(struct common_sampler * gsmpl, struct llama_context * ctx, int idx, bool grammar_first = false);
llama_token common_sampler_sample(struct common_sampler * gsmpl, struct llama_context * ctx, int idx);
// generalized version of common_sampler_sample
//
@@ -80,10 +75,10 @@ llama_token common_sampler_sample(struct common_sampler * gsmpl, struct llama_co
//
// returns at least 1 token, up to idxs.size()
//
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const std::vector<int> & idxs, const llama_tokens & draft, bool grammar_first = false);
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const std::vector<int> & idxs, const llama_tokens & draft);
// assume idxs == [ 0, 1, 2, ..., draft.size() ]
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const llama_tokens & draft, bool grammar_first = false);
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const llama_tokens & draft);
uint32_t common_sampler_get_seed(const struct common_sampler * gsmpl);