Morph MORPH
SIGN IN SIGN UP
ggml-org / llama.cpp UNCLAIMED

LLM inference in C/C++

101214 0 0 C++

COMMITS

/ common/sampling.cpp
master
March 31, 2026
G
common : Disable backend sampling if reasoning budget is enabled (#21209)
Galunid committed
5ce013c
March 27, 2026
A
common : inhibit lazy grammar sampler while reasoning is active (#20970)
Aldehir Rojas committed
59d8402
March 19, 2026
P
common/parser: add proper reasoning tag prefill reading (#20424)
Piotr Wilkin (ilintar) committed
5e54d51
March 11, 2026
P
common/parser: handle reasoning budget (#20297)
Piotr Wilkin (ilintar) committed
acb7c79
January 15, 2026
D
llama : add adaptive-p sampler (#17927)
ddh0 committed
13f1e4a
G
context : reserve new scheduler when graph topology changes (#18547)
Georgi Gerganov committed
39173bc
January 4, 2026
D
sampling : add support for backend sampling (#17004)
Daniel Bevenius committed
d3dce4e
January 3, 2026
A
common/grammar : replace problematic backtracking regex `[\s\S]*` (#18342)
Aldehir Rojas committed
cef1d23
December 17, 2025
G
common : restore grammar-based rejection sampling (#18137)
Georgi Gerganov committed
4301e27
December 14, 2025
G
common : refactor common_sampler + grammar logic changes (#17937)
Georgi Gerganov committed
254098a
November 20, 2025
G
common : more accurate sampling timing (#17382)
Georgi Gerganov committed
196f508
September 24, 2025
J
llama: print memory breakdown on exit (#15860)
Johannes Gäßler committed
e789095
August 31, 2025
G
sampling : optimize samplers by reusing bucket sort (#15665)
Georgi Gerganov committed
e92d53b
May 25, 2025
O
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
Olivier Chafik committed
f5cd27b
May 7, 2025
Y
common : Add a warning when we can't match samplers from a string or char. (#13330)
Ycros committed
39e73ae
May 5, 2025
O
sampling : Integrate Top-nσ into main sampling chain (and add it to the server) (#13264)
oobabooga committed
233461f
March 28, 2025
J
llama: fix error on bad grammar (#12628)
Johannes Gäßler committed
dd373dd
March 5, 2025
O
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
Olivier Chafik committed
669912d
March 4, 2025
M
ggml : portability fixes for VS 2017 (#12150)
mgroeber9110 committed
5bbe6a9
February 13, 2025
O
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
Olivier Chafik committed
c7f460a
V
sampling: add Top-nσ sampler (#11223)
Vinesh Janarthanan committed
27e8a23
February 2, 2025
M
sampling : support for llguidance grammars (#10224)
Michał Moskal committed
ff22770
January 30, 2025
O
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
Olivier Chafik committed
8b576b6
January 12, 2025
G
llama : add `llama_vocab`, functions -> methods, naming (#11110)
Georgi Gerganov committed
afa8a9e
December 16, 2024
G
sampling : refactor + optimize penalties sampler (#10803)
Georgi Gerganov committed
644fd71
November 25, 2024
G
speculative : refactor and add a simpler example (#10362)
Georgi Gerganov committed
d9d54e4
October 29, 2024
G
llama : remove Tail-Free sampling (#10071)
Georgi Gerganov committed
8d8ff71
October 25, 2024
W
llama : add DRY sampler (#9702)
wwoodsTM committed
ff252ea
October 21, 2024
G
llama : default sampling changes + greedy update (#9897)
Georgi Gerganov committed
55e4778
October 15, 2024
G
llama : add infill sampler (#9896)
Georgi Gerganov committed
755a9b2
M
sampling : add XTC sampler (#9742)
MaggotHATE committed
fbc98b7
October 10, 2024
D
common : use common_ prefix for common library functions (#9805)
Diego Devesa committed
7eee341
September 24, 2024
G
sampling : avoid expensive softmax during greedy sampling (#9605)
Georgi Gerganov committed
b0f2736
September 15, 2024
G
common : reimplement logging (#9418)
Georgi Gerganov committed
6262d13
September 13, 2024
G
llama : llama_perf + option to disable timings during decode (#9355)
Georgi Gerganov committed
0abc6a2
September 10, 2024
S
llama : move random seed generation to the samplers (#9398)
slaren committed
49006c6
September 9, 2024
X
common : move arg parser code to `arg.cpp` (#9388)
Xuan Son Nguyen committed
bfe76d4
September 7, 2024
G
llama : fix empty ring buffer push (#9358)
Georgi Gerganov committed
f12295b
G
llama : refactor sampling v2 (#9294)
Georgi Gerganov committed
df270ef
July 23, 2024
G
llama : move vocab, grammar and sampling into separate files (#8508)
Georgi Gerganov committed
938943c
July 8, 2024
K
common : preallocate sampling token data vector (#8363)
Kevin Wang committed
470939d
K
common : avoid unnecessary logits fetch (#8358)
Kevin Wang committed
ffd0079
June 25, 2024
D
llama : return nullptr from llama_grammar_init (#8093)
Daniel Bevenius committed
e6bf007
May 22, 2024
G
common : normalize naming style (#7462)
Georgi Gerganov committed
6ff1398
May 21, 2024
O
`grammars`: fix resampling logic regression (#7424)
Olivier Chafik committed
e402de3
May 11, 2024
J
server: fix reported top tokens for temperature 0 (#7203)
Johannes Gäßler committed
5ae3426
May 7, 2024
J
server: fix incorrectly reported token probabilities (#7125)
Johannes Gäßler committed
af0a5b6
April 29, 2024
D
sampling : use std::random_device{}() for default random seed (#6962)
David Renshaw committed
3f16747
April 24, 2024
J
Server: fix seed for multiple slots (#6835)
Johannes Gäßler committed
28103f4
March 24, 2024
M
sampling : deduplicated code for probability distribution access (#6240)
Minsoo Cheong committed
586e7bc