 Georgi Gerganov
|
381da2d9f0
metal : build metallib + fix embed path (#6015)
|
il y a 1 an |
 slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
il y a 1 an |
|
Georgi Gerganov
|
83796e62bc
llama : refactor unicode stuff (#5992)
|
il y a 1 an |
 DAN™
|
bcebd7dbf6
llama : add support for GritLM (#5959)
|
il y a 1 an |
|
Georgi Gerganov
|
8a3012a4ad
ggml : add ggml-common.h to deduplicate shared code (#5940)
|
il y a 1 an |
 Gabe Goodhart
|
e1fa9569ba
server : add SSL support (#5926)
|
il y a 1 an |
|
Georgi Gerganov
|
2002bc96bf
server : refactor (#5882)
|
il y a 1 an |
 le.chang
|
cbbd1efa06
Makefile: use variables for cublas (#5689)
|
il y a 1 an |
 kwin1412
|
f1a98c5254
make : fix nvcc version is empty (#5713)
|
il y a 1 an |
 CJ Pais
|
6560bed3f0
server : support llava 1.6 (#5553)
|
il y a 1 an |
|
slaren
|
06bf2cf8c4
make : fix debug build with CUDA (#5616)
|
il y a 1 an |
 Haoxiang Fei
|
8dbbd75754
metal : add build system support for embedded metal library (#5604)
|
il y a 1 an |
 Jared Van Bortel
|
f24ed14ee0
make : pass CPPFLAGS directly to nvcc, not via -Xcompiler (#5598)
|
il y a 1 an |
|
Georgi Gerganov
|
d0e3ce51f4
ci : enable -Werror for CUDA builds (#5579)
|
il y a 1 an |
|
Georgi Gerganov
|
68a6b98b3c
make : fix CUDA build (#5580)
|
il y a 1 an |
 Xuan Son Nguyen
|
11b12de39b
llama : add llama_chat_apply_template() (#5538)
|
il y a 1 an |
|
Jared Van Bortel
|
a0c2dad9d4
build : pass all warning flags to nvcc via -Xcompiler (#5570)
|
il y a 1 an |
 Ananta Bastola
|
6e4e973b26
ci : add an option to fail on compile warning (#3952)
|
il y a 1 an |
 Johannes Gäßler
|
ad014bba97
make: add error message for bad CUDA version (#5444)
|
il y a 1 an |
|
Johannes Gäßler
|
098f6d737b
make: Use ccache for faster compilation (#5318)
|
il y a 1 an |
|
Johannes Gäßler
|
3c0d25c475
make: add nvcc info print (#5310)
|
il y a 1 an |
|
Johannes Gäßler
|
3cc5ed353c
make: fix nvcc optimization flags for host code (#5309)
|
il y a 1 an |
 0cc4m
|
e920ed393d
Vulkan Intel Fixes, Optimizations and Debugging Flags (#5301)
|
il y a 1 an |
 Ali Nehzat
|
d71ac90985
make : generate .a library for static linking (#5205)
|
il y a 2 ans |
|
0cc4m
|
2307523d32
ggml : add Vulkan backend (#2059)
|
il y a 2 ans |
|
Xuan Son Nguyen
|
48c857aa10
server : refactored the task processing logic (#5065)
|
il y a 2 ans |
 crasm
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
il y a 2 ans |
|
Georgi Gerganov
|
c918fe8dca
metal : create autorelease pool during library build (#4970)
|
il y a 2 ans |
|
Georgi Gerganov
|
4be5ef556d
metal : remove old API (#4919)
|
il y a 2 ans |
 Kawrakow
|
326b418b59
Importance Matrix calculation (#4861)
|
il y a 2 ans |
