 Georgi Gerganov
|
3a0345970e
make : whitespace
|
1 rok temu |
 Jared Van Bortel
|
32c8486e1f
wpm : portable unicode tolower (#6305)
|
1 rok temu |
 slaren
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
1 rok temu |
|
slaren
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 rok temu |
 Minsoo Cheong
|
64e7b47c69
examples : add "retrieval" (#6193)
|
1 rok temu |
 Pierrick Hymbert
|
21cad01b6e
split: add gguf-split in the make build target (#6262)
|
1 rok temu |
 Johannes Gäßler
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
1 rok temu |
|
slaren
|
2f0e81e053
cuda : add LLAMA_CUDA_NO_PEER_COPY to workaround broken ROCm p2p copy (#6208)
|
1 rok temu |
 Olivier Chafik
|
5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
|
1 rok temu |
|
Pierrick Hymbert
|
d0d5de42e5
gguf-split: split and merge gguf per batch of tensors (#6135)
|
1 rok temu |
|
Pierrick Hymbert
|
d01b3c4c32
common: llama_load_model_from_url using --model-url (#6098)
|
1 rok temu |
|
Georgi Gerganov
|
131b058409
make : ggml-metal.o depends on ggml.h
|
1 rok temu |
|
Georgi Gerganov
|
381da2d9f0
metal : build metallib + fix embed path (#6015)
|
1 rok temu |
|
slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
1 rok temu |
|
Georgi Gerganov
|
83796e62bc
llama : refactor unicode stuff (#5992)
|
1 rok temu |
 DAN™
|
bcebd7dbf6
llama : add support for GritLM (#5959)
|
1 rok temu |
|
Georgi Gerganov
|
8a3012a4ad
ggml : add ggml-common.h to deduplicate shared code (#5940)
|
1 rok temu |
 Gabe Goodhart
|
e1fa9569ba
server : add SSL support (#5926)
|
1 rok temu |
|
Georgi Gerganov
|
2002bc96bf
server : refactor (#5882)
|
1 rok temu |
 le.chang
|
cbbd1efa06
Makefile: use variables for cublas (#5689)
|
1 rok temu |
 kwin1412
|
f1a98c5254
make : fix nvcc version is empty (#5713)
|
1 rok temu |
 CJ Pais
|
6560bed3f0
server : support llava 1.6 (#5553)
|
1 rok temu |
|
slaren
|
06bf2cf8c4
make : fix debug build with CUDA (#5616)
|
1 rok temu |
 Haoxiang Fei
|
8dbbd75754
metal : add build system support for embedded metal library (#5604)
|
1 rok temu |
|
Jared Van Bortel
|
f24ed14ee0
make : pass CPPFLAGS directly to nvcc, not via -Xcompiler (#5598)
|
1 rok temu |
|
Georgi Gerganov
|
d0e3ce51f4
ci : enable -Werror for CUDA builds (#5579)
|
1 rok temu |
|
Georgi Gerganov
|
68a6b98b3c
make : fix CUDA build (#5580)
|
1 rok temu |
 Xuan Son Nguyen
|
11b12de39b
llama : add llama_chat_apply_template() (#5538)
|
1 rok temu |
|
Jared Van Bortel
|
a0c2dad9d4
build : pass all warning flags to nvcc via -Xcompiler (#5570)
|
1 rok temu |
 Ananta Bastola
|
6e4e973b26
ci : add an option to fail on compile warning (#3952)
|
1 rok temu |
