 Georgi Gerganov
|
4d98d9a656
sync : ggml (SD ops, tests, kernels) (#4444)
|
2 years ago |
 slaren
|
799a1cb13b
llama : add Mixtral support (#4406)
|
2 years ago |
|
Georgi Gerganov
|
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
|
2 years ago |
|
Georgi Gerganov
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
2 years ago |
|
Georgi Gerganov
|
d7b800b8bc
llama : pad KV cache size (#4280)
|
2 years ago |
|
Georgi Gerganov
|
ef47ec18da
ggml : add ggml_soft_max_ext (#4256)
|
2 years ago |
 Xiao-Yong Jin
|
22da05536f
metal : fix yarn (#4220)
|
2 years ago |
|
Georgi Gerganov
|
4f447a4833
llama : fix data units (#4101)
|
2 years ago |
|
Georgi Gerganov
|
3d68f364f1
ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060)
|
2 years ago |
|
Georgi Gerganov
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
2 years ago |
 Peter Sugihara
|
d9b33fe95b
metal : round up to 16 to fix MTLDebugComputeCommandEncoder assertion (#3938)
|
2 years ago |
|
Xiao-Yong Jin
|
5ba3746171
ggml-metal: fix yarn rope (#3937)
|
2 years ago |
|
Georgi Gerganov
|
183b3fac6c
metal : fix build errors and kernel sig after #2268 (#3898)
|
2 years ago |
 cebtenzzre
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 years ago |
|
Georgi Gerganov
|
e16b9fa4ba
metal : multi-simd softmax (#3710)
|
2 years ago |
|
Georgi Gerganov
|
71e3718abd
llama : refactor graph build code (#3837)
|
2 years ago |
 Aarni Koskela
|
82a6646e02
metal : try cwd for ggml-metal.metal if bundle lookup fails (#3793)
|
2 years ago |
|
Georgi Gerganov
|
469c9addef
metal : handle ggml_scale for n%4 != 0 (close #3754)
|
2 years ago |
 Jhen-Jie Hong
|
c67fe68e41
metal : implement q5_0 and q5_1 kernels (#3648)
|
2 years ago |
 Jan Ploski
|
f5f9121de1
llm : add MPT support (#3417)
|
2 years ago |
|
Georgi Gerganov
|
fcca0a7004
refact : fix convert script + zero out KV cache to avoid nans (#3523)
|
2 years ago |
|
Georgi Gerganov
|
dcc09d2596
metal : do not use mul_mm kernels when ne00 < 64 (#3542)
|
2 years ago |
|
Georgi Gerganov
|
db3abcc114
sync : ggml (ggml-backend) (#3548)
|
2 years ago |
|
Georgi Gerganov
|
94e502dfb7
ci : enable on obj-c changes + fix metal build (#3540)
|
2 years ago |
|
Georgi Gerganov
|
b0ec5218c3
metal : support MTLGPUFamily < Apple7, formatting, style (#3524)
|
2 years ago |
|
Jhen-Jie Hong
|
c26765a0a1
metal : support default.metallib load & reuse code for swift package (#3522)
|
2 years ago |
 Phillip Kravtsov
|
0e797c2fc5
llm : support Adept Persimmon 8B (#3410)
|
2 years ago |
 Jiahao Li
|
f56e1baec3
metal : alibi for arbitrary number of heads (#3426)
|
2 years ago |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 years ago |
 Rickard Hallerbäck
|
dc6897404e
metal : reusing llama.cpp logging (#3152)
|
2 years ago |
