tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : support negative ith in llama_get_ API (#6519)

Browse Source 
* llama_sampling_sample with default args is more naively usable

* Batches populated by either llama_batch_get_one or llama_batch_add work with default args
  * Previously get_one could use the default argument
  * Previously add should usually have used the last index where logits[idx] == true
* This hopefully encourages the use of llama_batch_add
  * By giving expected results when using default arguments.
* Adds "negative indexing" feature to llama_get_logits_ith and llama_get_embeddings_ith
* Believed to work with any currently well behaved program
  * Default arg now works for both cases (previously would give strange results for add case)
  * Any non-negative number is unaffected and behaves as previously
  * Negative arguments were previously invalid.
* Implemented as a special case of indexing as suggested by @compilade in https://github.com/ggerganov/llama.cpp/pull/6519

* Fixed mismatch type errors

* cited in macOS CI tests
* Missed in original updates based on PR feedback in https://github.com/ggerganov/llama.cpp/pull/6519
This commit is contained in:
Rick G
2024-04-08 06:02:30 -07:00
committed by GitHub
parent beea6e1b16
commit e3c337d87c
3 changed files with 34 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/sampling.h
View File

@@ -129,7 +129,7 @@ llama_token llama_sampling_sample(
struct llama_sampling_context * ctx_sampling,
struct llama_context * ctx_main,
struct llama_context * ctx_cfg,
int idx = 0);
int idx = -1);
// Prepares and adjusts the set of token candidates for sampling based on penalties, biases, and sampling parameters.
llama_token_data_array llama_sampling_prepare(