 Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 年之前 |
 slaren
|
097e121e2f
llama : add benchmark example (#2626)
|
2 年之前 |
 drbh
|
ee77efea2a
test : add simple grammar parsing tests (#2594)
|
2 年之前 |
 byte-6174
|
b19edd54d5
Adding support for llama2.c models (#2559)
|
2 年之前 |
|
Georgi Gerganov
|
3973b25a64
gitignore : fix final newline
|
2 年之前 |
 Jose Maldonado
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 年之前 |
 Jiří Podivín
|
54e3bc76fe
make : add new target for test binaries (#2244)
|
2 年之前 |
|
Georgi Gerganov
|
d01bccde9f
ci : integrate with ggml-org/ci (#2250)
|
2 年之前 |
 Evan Miller
|
5656d10599
mpi : add support for distributed inference via MPI (#2099)
|
2 年之前 |
 ningshanwutuobang
|
cfa0750bc9
llama : support input embeddings directly (#1910)
|
2 年之前 |
|
Georgi Gerganov
|
051e1b0e6a
llama : fix kv_cache `n` init (close #1903)
|
2 年之前 |
 Randall Fitzgerald
|
794db3e7b9
Server Example Refactor and Improvements (#1570)
|
2 年之前 |
 Borislav Stanimirov
|
602c748863
gitignore : add several entries specific to Visual Studio (#1888)
|
2 年之前 |
 daboe01
|
cf267d1c71
make : add train-text-from-scratch (#1850)
|
2 年之前 |
|
Georgi Gerganov
|
2d43387daf
ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710)
|
2 年之前 |
|
Georgi Gerganov
|
7ad7750c5c
gitignore : add .clang-tidy
|
2 年之前 |
|
Georgi Gerganov
|
ecb217db4f
llama : Metal inference (#1642)
|
2 年之前 |
|
Georgi Gerganov
|
0cd22e190a
llama : fix various warnings
|
2 年之前 |
|
Georgi Gerganov
|
b9fd7eee57
ggml : remove bit shuffling (#1405)
|
2 年之前 |
|
Georgi Gerganov
|
f9a6364912
llama : require first token to be BOS (#1303)
|
2 年之前 |
 Jed Fox
|
3924088512
Remove default arguments from sampling functions (#1343)
|
2 年之前 |
 DannyDaemonic
|
f4cef87edf
Add git-based build information for better issue tracking (#1232)
|
2 年之前 |
 Stephan Walter
|
f0d70f147d
Various fixes to mat_mul benchmark (#1253)
|
2 年之前 |
 CRD716
|
5fba3c016b
examples : add Jeopardy example (#1168)
|
2 年之前 |
|
Georgi Gerganov
|
574406dc7e
ggml : add Q5_0 and Q5_1 quantization (#1187)
|
2 年之前 |
|
Georgi Gerganov
|
884e7d7a2b
ggml : use 8-bit precision for Q4_1 intermediate results (#1047)
|
2 年之前 |
|
Georgi Gerganov
|
4caebf6d40
gitignore : vdot
|
2 年之前 |
|
Georgi Gerganov
|
c85980acd0
gitignore : benchmark
|
2 年之前 |
 unbounded
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
2 年之前 |
 iacore
|
ed1c214e66
zig : add build.zig (#773)
|
2 年之前 |
