 ssweens
|
4529c660c8
kv-cache: Fix state restore fragmented cache (#17982)
|
1 miesiąc temu |
 Aldehir Rojas
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
1 miesiąc temu |
 Diego Devesa
|
e072b2052e
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276)
|
1 miesiąc temu |
 Aaron Teo
|
624207e676
devops: add s390x & ppc64le CI (#15925)
|
3 miesięcy temu |
 Acly
|
f2a789e334
ggml : split graph allocations according to backend max buffer size (#15815)
|
3 miesięcy temu |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 miesięcy temu |
 Georgi Gerganov
|
00131d6eaf
tests : update for LLAMA_SET_ROWS=1 (#14961)
|
5 miesięcy temu |
|
Diego Devesa
|
6adc3c3ebc
llama : add thread safety test (#14035)
|
7 miesięcy temu |
 Sigbjørn Skjæret
|
d4e0d95cf5
chore : clean up relative source dir paths (#14128)
|
7 miesięcy temu |
|
Sigbjørn Skjæret
|
cc66a7f78f
tests : add test-tokenizers-repo (#14017)
|
7 miesięcy temu |
|
Diego Devesa
|
7f4fbe5183
llama : allow building all tests on windows when not using shared libs (#13980)
|
7 miesięcy temu |
 Xuan-Son Nguyen
|
07e4351ce6
convert : allow partial update to the chkhsh pre-tokenizer list (#13847)
|
7 miesięcy temu |
|
Sigbjørn Skjæret
|
aa50ba462f
tests : improve UGM tokenizer test coverage (#13773)
|
7 miesięcy temu |
 Olivier Chafik
|
f5cd27b71d
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
|
7 miesięcy temu |
 Olivier Chafik
|
3198405e98
`common`: add partial regex support (#12808)
|
8 miesięcy temu |
|
Xuan-Son Nguyen
|
27aa259532
mtmd : add C public API (#13184)
|
8 miesięcy temu |
|
Diego Devesa
|
9f2da5871f
llama : build windows releases with dl backends (#13220)
|
8 miesięcy temu |
|
Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 miesięcy temu |
|
Georgi Gerganov
|
13b4548877
cmake : do not include ./src as public for libllama (#13062)
|
8 miesięcy temu |
|
Xuan-Son Nguyen
|
bd3f59f812
cmake : enable curl by default (#12761)
|
9 miesięcy temu |
 Michał Moskal
|
ff227703d6
sampling : support for llguidance grammars (#10224)
|
11 miesięcy temu |
|
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 miesięcy temu |
|
Georgi Gerganov
|
4dd34ff831
cmake : add sanitizer flags for llama.cpp (#11279)
|
1 rok temu |
 Johannes Gäßler
|
081b29bd2a
tests: add tests for GGUF (#10830)
|
1 rok temu |
|
Diego Devesa
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 rok temu |
|
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 rok temu |
|
Georgi Gerganov
|
84274a10c3
tests : remove test-grad0
|
1 rok temu |
 Max Krasnyansky
|
0226613853
threadpool : skip polling for unused threads (#9461)
|
1 rok temu |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
1 rok temu |
 Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
1 rok temu |
