 slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
1 rok temu |
 SeungWon Jeong
|
fb215c3832
server : normalize embeddings (#5956)
|
1 rok temu |
 Georgi Gerganov
|
29ae62d2ae
llama : fix embeddings (#5796)
|
1 rok temu |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 rok temu |
 Douglas Hanley
|
03bf161eb6
llama : support batched embeddings (#5466)
|
1 rok temu |
|
Douglas Hanley
|
2891c8aa9a
Add support for BERT embedding models (#5423)
|
1 rok temu |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 lat temu |
|
slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 lat temu |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 lat temu |
|
Cebtenzzre
|
8781013ef6
make : restore build-info.h dependency for several targets (#3205)
|
2 lat temu |
|
Cebtenzzre
|
e6616cf0db
examples : add compiler version and target to build info (#2998)
|
2 lat temu |
|
Cebtenzzre
|
e64f5b5578
examples : make n_ctx warning work again (#3066)
|
2 lat temu |
|
Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
2 lat temu |
|
Georgi Gerganov
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 lat temu |
|
slaren
|
519c981f8b
embedding : evaluate prompt in batches (#2713)
|
2 lat temu |
|
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 lat temu |
 Evan Miller
|
5656d10599
mpi : add support for distributed inference via MPI (#2099)
|
2 lat temu |
 Judd
|
36680f6e40
convert : update for baichuan (#2081)
|
2 lat temu |
 Howard Su
|
b8c8dda75f
Use unsigned for random seed (#2006)
|
2 lat temu |
 zrm
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
 Didzis Gosko
|
527b6fba1d
llama : make model stateless and context stateful (llama_state) (#1797)
|
2 lat temu |
 Borislav Stanimirov
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
2 lat temu |
|
Georgi Gerganov
|
ec2e10c444
llama : add llama_init_backend() API (close #1527)
|
2 lat temu |
 András Salamon
|
9560655409
define default model path once, sync path with readme (#1366)
|
2 lat temu |
 Rinne
|
6456a4eb9f
embedding : remove unused code (#1426)
|
2 lat temu |
 Ron Evans
|
67c77799e0
examples : add llama_init_from_gpt_params() common function (#1290)
|
2 lat temu |
 Robert Brisita
|
2bb992f034
llama : allow 0 as a seed number. (#1275)
|
2 lat temu |
 DannyDaemonic
|
f4cef87edf
Add git-based build information for better issue tracking (#1232)
|
2 lat temu |
 Pavol Rusnak
|
489537e6cf
examples: add missing <ctime> include for time() (#1011)
|
2 lat temu |
 comex
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 lat temu |
