Update llama.cpp

This commit is contained in:
Andrei Betlen 2023-06-05 18:17:29 -04:00
parent 18c7b8520e
commit 7b57420ea9
3 changed files with 21 additions and 1 deletions

View file

@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
- Added: k-quants support
## [v0.1.58]
- Added: Metal Silicon support

View file

@ -191,6 +191,15 @@ llama_context_params_p = POINTER(llama_context_params)
# LLAMA_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q5_1 = 9, // except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q2_K = 10,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q3_K_S = 11,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q3_K_M = 12,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q3_K_L = 13,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q4_K_S = 14,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q4_K_M = 15,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q5_K_S = 16,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q5_K_M = 17,// except 1d tensors
# LLAMA_FTYPE_MOSTLY_Q6_K = 18,// except 1d tensors
# };
LLAMA_FTYPE_ALL_F32 = c_int(0)
LLAMA_FTYPE_MOSTLY_F16 = c_int(1)
@ -200,6 +209,15 @@ LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = c_int(4)
LLAMA_FTYPE_MOSTLY_Q8_0 = c_int(7)
LLAMA_FTYPE_MOSTLY_Q5_0 = c_int(8)
LLAMA_FTYPE_MOSTLY_Q5_1 = c_int(9)
LLAMA_FTYPE_MOSTLY_Q2_K = c_int(10)
LLAMA_FTYPE_MOSTLY_Q3_K_S = c_int(11)
LLAMA_FTYPE_MOSTLY_Q3_K_M = c_int(12)
LLAMA_FTYPE_MOSTLY_Q3_K_L = c_int(13)
LLAMA_FTYPE_MOSTLY_Q4_K_S = c_int(14)
LLAMA_FTYPE_MOSTLY_Q4_K_M = c_int(15)
LLAMA_FTYPE_MOSTLY_Q5_K_S = c_int(16)
LLAMA_FTYPE_MOSTLY_Q5_K_M = c_int(17)
LLAMA_FTYPE_MOSTLY_Q6_K = c_int(18)
# LLAMA_API struct llama_context_params llama_context_default_params();

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit 827f5eda91e5b7299848ee2c7179d873bdee0f7b
Subproject commit f4c55d3bd7e124b101bc974cbbf0e0dbbc32d5a3