 Olivier Chafik
|
5cf5e7d490
`build`: generate hex dump of server assets during build (#6661)
|
1 سال پیش |
 Georgi Gerganov
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
1 سال پیش |
|
Georgi Gerganov
|
3b8f1ec4b1
llamafile : tmp disable + build sgemm.o when needed (#6716)
|
1 سال پیش |
|
Georgi Gerganov
|
666867b799
ggml : fix llamafile sgemm wdata offsets (#6710)
|
1 سال پیش |
 Justine Tunney
|
8cc91dc63c
ggml : add llamafile sgemm (#6414)
|
1 سال پیش |
|
Olivier Chafik
|
7593639ce3
`main`: add --json-schema / -j flag (#6659)
|
1 سال پیش |
 Nikolas
|
a474f50ebb
Refactor Error Handling for CUDA (#6575)
|
1 سال پیش |
 Pierrick Hymbert
|
b804b1ef77
eval-callback: Example how to use eval callback for debugging (#6576)
|
1 سال پیش |
 Clint Herron
|
57dd02c44b
Tests: Added integration tests for GBNF parser (#6472)
|
1 سال پیش |
|
Clint Herron
|
9b84ae1806
examples : add GBNF validator program (#5948)
|
1 سال پیش |
|
Georgi Gerganov
|
3a0345970e
make : whitespace
|
1 سال پیش |
 Jared Van Bortel
|
32c8486e1f
wpm : portable unicode tolower (#6305)
|
1 سال پیش |
 slaren
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
1 سال پیش |
|
slaren
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 سال پیش |
 Minsoo Cheong
|
64e7b47c69
examples : add "retrieval" (#6193)
|
1 سال پیش |
|
Pierrick Hymbert
|
21cad01b6e
split: add gguf-split in the make build target (#6262)
|
1 سال پیش |
 Johannes Gäßler
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
1 سال پیش |
|
slaren
|
2f0e81e053
cuda : add LLAMA_CUDA_NO_PEER_COPY to workaround broken ROCm p2p copy (#6208)
|
1 سال پیش |
|
Olivier Chafik
|
5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
|
1 سال پیش |
|
Pierrick Hymbert
|
d0d5de42e5
gguf-split: split and merge gguf per batch of tensors (#6135)
|
1 سال پیش |
|
Pierrick Hymbert
|
d01b3c4c32
common: llama_load_model_from_url using --model-url (#6098)
|
1 سال پیش |
|
Georgi Gerganov
|
131b058409
make : ggml-metal.o depends on ggml.h
|
1 سال پیش |
|
Georgi Gerganov
|
381da2d9f0
metal : build metallib + fix embed path (#6015)
|
1 سال پیش |
|
slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
1 سال پیش |
|
Georgi Gerganov
|
83796e62bc
llama : refactor unicode stuff (#5992)
|
1 سال پیش |
 DAN™
|
bcebd7dbf6
llama : add support for GritLM (#5959)
|
1 سال پیش |
|
Georgi Gerganov
|
8a3012a4ad
ggml : add ggml-common.h to deduplicate shared code (#5940)
|
1 سال پیش |
 Gabe Goodhart
|
e1fa9569ba
server : add SSL support (#5926)
|
1 سال پیش |
|
Georgi Gerganov
|
2002bc96bf
server : refactor (#5882)
|
1 سال پیش |
 le.chang
|
cbbd1efa06
Makefile: use variables for cublas (#5689)
|
1 سال پیش |
