baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

feat: Update llama.cpp

Browse source
This commit is contained in:
Andrei Betlen 2024-04-25 02:48:26 -04:00
parent c50d3300d2
commit 2a9979fce1
2 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
llama_cpp/llama_cpp.py
View file

@ -1167,7 +1167,13 @@ def llama_n_seq_max(ctx: llama_context_p, /) -> int:
...
# LLAMA_API enum llama_vocab_type llama_vocab_type(const struct llama_model * model);
# LLAMA_API enum llama_pooling_type llama_pooling_type(const struct llama_context * ctx);
@ctypes_function("llama_pooling_type", [llama_context_p_ctypes], ctypes.c_int)
def llama_pooling_type(ctx: llama_context_p, /) -> int:
...
# LLAMA_API enum llama_vocab_type llama_vocab_type (const struct llama_model * model);
@ctypes_function("llama_vocab_type", [llama_model_p_ctypes], ctypes.c_int)
def llama_vocab_type(model: llama_model_p, /) -> int:
...
@ -3091,7 +3097,7 @@ def llama_sample_token_greedy(
...
# /// @details Randomly selects a token from the candidates based on their probabilities.
# /// @details Randomly selects a token from the candidates based on their probabilities using the RNG of ctx.
# LLAMA_API llama_token llama_sample_token(
# struct llama_context * ctx,
# llama_token_data_array * candidates);

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit 4e96a812b3ce7322a29a3008db2ed73d9087b176
Subproject commit 784e11dea1f5ce9638851b2b0dddb107e2a609c8