 Georgi Gerganov
|
2a4e41a086
llama : fix compile warnings
|
2 lat temu |
 Johannes Gäßler
|
17366df842
Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
|
2 lat temu |
|
Georgi Gerganov
|
44f906e853
metal : add f16 support
|
2 lat temu |
 LostRuins
|
d5b111f53d
Clblast fixes + enhancements to save VRAM and offload more layers (#1675)
|
2 lat temu |
|
Georgi Gerganov
|
2d43387daf
ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710)
|
2 lat temu |
|
Georgi Gerganov
|
7ad7750c5c
gitignore : add .clang-tidy
|
2 lat temu |
|
Georgi Gerganov
|
7a74dee6b4
llama : temporary disable Q6_K output quantization (#1711)
|
2 lat temu |
 Spencer Sutton
|
590250f7a9
metal : add checks for buffer size (#1706)
|
2 lat temu |
 Yuval Peled
|
f4c55d3bd7
docs : add performance troubleshoot + example benchmark documentation (#1674)
|
2 lat temu |
 Foul-Tarnished
|
f1465624c2
readme : fix typo (#1700)
|
2 lat temu |
 mgroeber9110
|
c2df36d60d
llama : consistently catch and throw only exceptions deriving from std::exception (#1599)
|
2 lat temu |
 kiltyj
|
9d0693bce3
metal : use shared buffers between CPU and GPU (#1696)
|
2 lat temu |
 grahameth
|
efe0507632
ggml : fix internal overflow in ggml_time_us on Windows (#1702)
|
2 lat temu |
|
Georgi Gerganov
|
e7fe66e670
ci : disable auto tidy (#1705)
|
2 lat temu |
 Kawrakow
|
99009e72f8
ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684)
|
2 lat temu |
 Henri Vasserman
|
5220a991a5
Increase 3B scratch buffers. (#1698)
|
2 lat temu |
|
Georgi Gerganov
|
d1f563a743
llama : fix Metal KV cache sync (close #1695)
|
2 lat temu |
|
Georgi Gerganov
|
827f5eda91
readme : update hot topics
|
2 lat temu |
|
Georgi Gerganov
|
ecb217db4f
llama : Metal inference (#1642)
|
2 lat temu |
 0cc4m
|
dcb2ed4826
OpenCL: Fix duplication of layers in VRAM and RAM, add GPU mul kernel (#1653)
|
2 lat temu |
|
Henri Vasserman
|
d8bd0013e8
Add info about CUDA_VISIBLE_DEVICES (#1682)
|
2 lat temu |
 Jiří Podivín
|
b5c85468a3
Docker: change to calling convert.py (#1641)
|
2 lat temu |
 Evan Jones
|
136476e898
Fix prompt cache saving and chat-persistent rollover (#1678)
|
2 lat temu |
|
Henri Vasserman
|
ffb06a345e
OpenLLaMA 3B support (#1588)
|
2 lat temu |
|
Georgi Gerganov
|
7552ac5863
ggml : sync cgraph import / export API
|
2 lat temu |
|
Georgi Gerganov
|
5d1830b99d
ggml : fix bug in ggml_alibi
|
2 lat temu |
 DannyDaemonic
|
248367605e
Work around for recalculating logits in cached prompts (Fixes #1585) (#1609)
|
2 lat temu |
|
Jiří Podivín
|
0e730dd23b
Adding git in container package dependencies (#1621)
|
2 lat temu |
|
Johannes Gäßler
|
3b126f654f
LLAMA_DEBUG adds debug symbols (#1617)
|
2 lat temu |
 Kerfuffle
|
1b78ed2081
Only show -ngl option when relevant + other doc/arg handling updates (#1625)
|
2 lat temu |
