FazBrowse GitHub Viewer | Trending | | Home

Tools: [Download Repo ZIP] [Original HTTPS Page]

History for include - allozaur/llama.cpp · GitHub

Commits

History for

Commits on Aug 4, 2026

sampler : remove "full-context windows" from history-based samplers (#26524)
ggerganov
authored
a6aa6f5
llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520)
ggerganov
authored
935cad6

Commits on Aug 3, 2026

CUDA: Add backend sampler for penalties sampler (#25262)
kmorennv
authored
96278e3

Commits on Jul 31, 2026

llama : load MTP tensors only if they are really used (#26296)

fairydreaming
and
sszymczy
authored
82dbc4f

Commits on Jul 29, 2026

llama: move suppress_tokens handling to common/sampling (#26276)
ngxson
authored
afeebe1

Commits on Jul 27, 2026

args: add `-lm mlock` where it mlocks but doesnt mmap (#26135)
taronaeo
authored
ad256de

Commits on Jul 23, 2026

args: refactor mlock/mmap/directio into load-mode (#20834)
taronaeo
authored
e6dd0e2

Commits on Jul 7, 2026

Add Q2_0 quantization: type definition and CPU backend (#24448)
khosravipasha
authored
bec4772

Commits on Jul 2, 2026

llama : add llama_model_ftype_name() (#25134)
angt
authored
fdb1db8

Commits on Jun 21, 2026

spec : Support Step3.5/3.7 flash mtp3 (#24340)

forforever73
and
am17an
authored
d789527

Commits on Jun 7, 2026

llama : add Gemma4 MTP (#23398)
am17an
authored
04eb4c4

Commits on Jun 2, 2026

llama : deprecate `llama_set_warmup` (#24009)

ggerganov
and
danbev
authored
4f3a4be

Commits on Jun 1, 2026

llama: limit max outputs of `llama_context` (#23861)
am17an
authored
de6f727

Commits on May 25, 2026

llama : document that only one on-device state can be saved per sequence (#23520)
TimNN
authored
314e729

Commits on May 16, 2026

llama + spec: MTP Support (#22673)

am17an
and
ggerganov
authored
2555826

Commits on May 11, 2026

spec : parallel drafting support (#22838)

ggerganov
and
Petros Sideris
authored
68e7ea3

Commits on May 5, 2026

llama : add option to save memory in device buffers (#22679)
ggerganov
authored
d6e7b03

Commits on Apr 21, 2026

fit-params : refactor + add option to output estimated memory per device (#22171)
ggerganov
authored
cfe9838

Commits on Apr 9, 2026

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

authored
d6f3030

Commits on Apr 6, 2026

ggml: add Q1_0 1-bit quantization support (CPU) (#21273)

khosravipasha
and
CISC
authored
2e1f0a8

Commits on Apr 1, 2026

llama : refactor llama_model_quantize_params to expose a pure C interface (#20346)

EAddario
and
ggerganov
authored
4951250

Commits on Mar 25, 2026

llama: fix llama-model-saver (#20503)

JohannesGaessler
and
Siddhesh2377
authored
36dafba

Commits on Mar 18, 2026

llama : re-enable manual LoRA adapter free (#19983)
PopFlamingo
authored
312cf03

Commits on Mar 11, 2026

ggml : add NVFP4 quantization type support (#19769)

richarddd
and
CISC
authored
5eae9cb

Commits on Mar 8, 2026

llama: end-to-end tests (#19802)
JohannesGaessler
authored
a976ff0

Commits on Mar 5, 2026

chore : correct typos [no ci] (#20041)

authored
92f7da0

Commits on Feb 20, 2026

quantize : add --dry-run option (#19526)

ddh0
and
CISC
authored
492bc31

Commits on Feb 14, 2026

llama : update LoRA API. + fix excessive graph reserves (#19280)

authored
2d8015e

Commits on Feb 12, 2026

llama : update outdated comment in llama.h (#19428)

MonkeybreadSoftware
and
danbev
authored
f488429

Commits on Feb 11, 2026

llama : correct typos 'occured' and 'occurences' (#19414)
thecaptain789
authored
8ee538c

Commits on Jan 28, 2026

llama : disable Direct IO by default (#19109)
ggerganov
authored
c5c64f7

Commits on Jan 25, 2026

llama: fix integer type consistency in split helpers (#18894)
MaheshJakkala
authored
24bc238

Commits on Jan 24, 2026

llama-fit-params: keep explicit --ctx-size 0 (#19070)
JohannesGaessler
authored
e9fd8dc

Commits on Jan 15, 2026

Back | FazBrowse Home | New Git URL