 Georgi Gerganov
|
2139667ec4
metal : fix out-of-bounds write (#11314)
|
пре 1 година |
|
Georgi Gerganov
|
80d0d6b4b7
common : add -hfd option for the draft model (#11318)
|
пре 1 година |
 Jeff Bolz
|
aea8ddd516
vulkan: fix coopmat2 validation failures (#11284)
|
пре 1 година |
|
Georgi Gerganov
|
9f7add1cde
examples : fix add_special conditions (#11311)
|
пре 1 година |
 Christopher Nielsen
|
90d987b105
mmap: add include for cerrno (#11296)
|
пре 1 година |
 Michael Podvitskiy
|
a4251edd6f
cmake: fix shell command quoting in build-info script (#11309)
|
пре 1 година |
 Xuan Son Nguyen
|
ec7f3ac9ab
llama : add support for Deepseek-R1-Qwen distill model (#11310)
|
пре 1 година |
|
Georgi Gerganov
|
ef6dada60c
cont : fix whitespaces (#11305)
|
пре 1 година |
 Kyle Bruene
|
ae3c1db2f9
llama : re-add LLM_ARCH_PHIMOE (#11305)
|
пре 1 година |
|
Georgi Gerganov
|
92bc493917
tests : increase timeout when sanitizers are enabled (#11300)
|
пре 1 година |
|
Georgi Gerganov
|
b9daaffe02
simple-chat : fix BOS being added to each message (#11278)
|
пре 1 година |
 Nicolò Scipione
|
99487b57d4
SYCL: Introducing memory host pool (#11251)
|
пре 1 година |
 Eric Curtin
|
a1649cc13f
Adding linenoise.cpp to llama-run (#11252)
|
пре 1 година |
|
Georgi Gerganov
|
4dd34ff831
cmake : add sanitizer flags for llama.cpp (#11279)
|
пре 1 година |
|
Xuan Son Nguyen
|
f30f099228
server : implement cancellable request (#11285)
|
пре 1 година |
|
Georgi Gerganov
|
f26c874179
scripts : restore hf.sh (#11288)
|
пре 1 година |
 LostRuins Concedo
|
6390a998bf
tts : add guide tokens support (#11186)
|
пре 1 година |
|
Jeff Bolz
|
44e18ef939
vulkan: fix coopmat2 flash attention for non-contiguous inputs (#11281)
|
пре 1 година |
 codezjx
|
3edfa7d375
llama.android: add field formatChat to control whether to parse special tokens when send message (#11270)
|
пре 1 година |
 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
пре 1 година |
|
Georgi Gerganov
|
a133566d34
vocab : fix double-eos check (#11273)
|
пре 1 година |
 David Renshaw
|
960ec65273
llama : fix deprecation message: vocabable -> vocab (#11269)
|
пре 1 година |
 musoles
|
7a689c415e
README : added kalavai to infrastructure list (#11216)
|
пре 1 година |
|
Jeff Bolz
|
bd38ddea01
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (#11166)
|
пре 1 година |
|
Jeff Bolz
|
466300fe14
vulkan: optimize coopmat2 q4_k/q5_k dequant functions. (#11206)
|
пре 1 година |
|
Jeff Bolz
|
206bc53422
vulkan: optimize coopmat2 q2_k dequant function (#11130)
|
пре 1 година |
 RunningLeon
|
4dbc8b9cb7
llama : add internlm3 support (#11233)
|
пре 1 година |
 Johannes Gäßler
|
9c8dcefe17
CUDA: backwards pass for misc. ops, add tests (#11257)
|
пре 1 година |
|
Xuan Son Nguyen
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
пре 1 година |
 fj-y-saito
|
c67cc9837d
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227)
|
пре 1 година |
