 Georgi Gerganov
|
18b35625c3
ggml : fix bug in LBFGS optimizer (found by ggml tests)
|
2 years ago |
 l3utterfly
|
ba4e85a833
llama : use aligned memory during ggml_init call from loading saved sessions (#1934)
|
2 years ago |
|
Georgi Gerganov
|
23fc5c219a
cmake : fix trailing whitespaces
|
2 years ago |
 Kawrakow
|
cb40dfca69
llama : only use Q6_K for output weights if tensor size is multiple of 256 (#1932)
|
2 years ago |
|
Kawrakow
|
ca7c3f4da5
cuda : faster k-quants on older GPUs (#1930)
|
2 years ago |
|
Georgi Gerganov
|
b97ca431db
ggml : sync latest ggml repo (#1924)
|
2 years ago |
 Howard Su
|
1e3abfcef0
cmake : fix build shared ggml when CUDA is enabled (#1929)
|
2 years ago |
 Johannes Gäßler
|
16b9cd1939
Convert vector to f16 for dequantize mul mat vec (#1913)
|
2 years ago |
|
Johannes Gäßler
|
b24c3049d9
Added tokens per second to info prints (#1928)
|
2 years ago |
|
Johannes Gäßler
|
0ede372a51
Fixed incorrectly applying RMS norm twice (#1925)
|
2 years ago |
|
l3utterfly
|
8596af4277
ggml : fix bug in ggml_compute_forward_add_q_f32 (#1918)
|
2 years ago |
 Mike
|
e1886cf4fe
readme : update Android build instructions (#1922)
|
2 years ago |
|
Kawrakow
|
8ab8ba62eb
llama : prevent usage of k-quants when tensor size is not a multiple of 256 (#1921)
|
2 years ago |
|
Kawrakow
|
90cc59d6ab
examples : fix examples/metal (#1920)
|
2 years ago |
|
Georgi Gerganov
|
ce2c7d72e2
metal : handle buffers larger than device's maxBufferLength (#1826)
|
2 years ago |
|
Howard Su
|
57cd69460f
cmake : add CUDA_ARCHITECTURES to new target ggml_static (#1917)
|
2 years ago |
|
Georgi Gerganov
|
b2416493ab
make : do not print help for simple example
|
2 years ago |
|
Georgi Gerganov
|
4f9c43e3bd
minor : warning fixes
|
2 years ago |
|
Johannes Gäßler
|
2c9380dd2f
Only one CUDA stream per device for async compute (#1898)
|
2 years ago |
|
Georgi Gerganov
|
051e1b0e6a
llama : fix kv_cache `n` init (close #1903)
|
2 years ago |
 DaniAndTheWeb
|
86c7571864
make : update for latest Arch (#1701)
|
2 years ago |
|
Howard Su
|
3d59ec5935
ggml : fix warnings under MSVC (#1908)
|
2 years ago |
 Aaron Miller
|
0711a5f6dc
metal : add norm, cpy f16->f16, alibi kernels (#1823)
|
2 years ago |
 Faez Shakil
|
fc45a81bc6
exposed modules so that they can be invoked by nix run github:ggerganov/llama.cpp#server etc (#1863)
|
2 years ago |
 Randall Fitzgerald
|
794db3e7b9
Server Example Refactor and Improvements (#1570)
|
2 years ago |
 Jiří Podivín
|
5ddf7ea1fb
hooks : setting up flake8 and pre-commit hooks (#1681)
|
2 years ago |
 Gustavo Rocha Dias
|
bac19927c3
readme : alternative way to build for Android with CLBlast. (#1828)
|
2 years ago |
 Kerfuffle
|
b4c6f46f17
Allow cmake to build ggml as a library (#1896)
|
2 years ago |
 David Yang
|
92f20d9942
train : get raw text instead of page with html (#1905)
|
2 years ago |
 0cc4m
|
d411968e99
opencl : support k-quants (#1836)
|
2 years ago |
