| .. |
|
peg-parser
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
há 1 mês atrás |
|
.gitignore
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
há 1 mês atrás |
|
CMakeLists.txt
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
há 1 mês atrás |
|
get-model.cpp
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
há 2 anos atrás |
|
get-model.h
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
há 2 anos atrás |
|
run-json-schema-to-grammar.mjs
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
há 8 meses atrás |
|
test-alloc.cpp
|
638d330246
ggml : fix graph reallocation with multiple chunks (#16396)
|
há 3 meses atrás |
|
test-arg-parser.cpp
|
4d5ae24c0a
arg: fix common_params_parse not accepting negated arg (#17991)
|
há 1 mês atrás |
|
test-autorelease.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
há 1 ano atrás |
|
test-backend-ops.cpp
|
303f8615e9
vulkan: Multi-pass softmax for large number of cols (#17892)
|
há 1 mês atrás |
|
test-barrier.cpp
|
e1f4921980
Fix race conditions in threadpool when dealing with dynamic/frequent n_threads changes (#17748)
|
há 1 mês atrás |
|
test-c.c
|
d4cdd9c1c3
ggml : remove kompute backend (#14501)
|
há 6 meses atrás |
|
test-chat-parser.cpp
|
2c301e91ab
common : handle unicode during partial json parsing (#16526)
|
há 3 meses atrás |
|
test-chat-peg-parser.cpp
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
há 1 mês atrás |
|
test-chat-template.cpp
|
c08002a198
chat : Granite Docling stopping (#16438)
|
há 3 meses atrás |
|
test-chat.cpp
|
2fbe3b7bb7
common : add parser for ministral/mistral large 3/devstral 2 (#17713)
|
há 1 mês atrás |
|
test-double-float.cpp
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
há 1 ano atrás |
|
test-gbnf-validator.cpp
|
13b4548877
cmake : do not include ./src as public for libllama (#13062)
|
há 8 meses atrás |
|
test-gguf.cpp
|
7675c555a1
gguf: fix failure on version == 0 (#13956)
|
há 7 meses atrás |
|
test-grammar-integration.cpp
|
e39502e74b
llama : add token matching support to llama-grammar (#17816)
|
há 1 mês atrás |
|
test-grammar-llguidance.cpp
|
13b4548877
cmake : do not include ./src as public for libllama (#13062)
|
há 8 meses atrás |
|
test-grammar-parser.cpp
|
e39502e74b
llama : add token matching support to llama-grammar (#17816)
|
há 1 mês atrás |
|
test-json-partial.cpp
|
2c301e91ab
common : handle unicode during partial json parsing (#16526)
|
há 3 meses atrás |
|
test-json-schema-to-grammar.cpp
|
c4357dcc35
Server: Change Invalid Schema from Server Error (500) to User Error (400) (#17572)
|
há 1 mês atrás |
|
test-llama-grammar.cpp
|
e39502e74b
llama : add token matching support to llama-grammar (#17816)
|
há 1 mês atrás |
|
test-log.cpp
|
7eee341bee
common : use common_ prefix for common library functions (#9805)
|
há 1 ano atrás |
|
test-lora-conversion-inference.sh
|
6c2131773c
cli: new CLI experience (#17824)
|
há 1 mês atrás |
|
test-model-load-cancel.cpp
|
47182dd03f
llama : update llama_model API names (#11063)
|
há 1 ano atrás |
|
test-mtmd-c-api.c
|
27aa259532
mtmd : add C public API (#13184)
|
há 8 meses atrás |
|
test-opt.cpp
|
bcbddcd54f
tests : fix test-opt with GGML_BACKEND_DL (#15599)
|
há 4 meses atrás |
|
test-peg-parser.cpp
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
há 1 mês atrás |
|
test-quantize-fns.cpp
|
e128a1bf5b
tests : fix test-quantize-fns to init the CPU backend (#12306)
|
há 10 meses atrás |
|
test-quantize-perf.cpp
|
bee378e098
ci: run the x64 and arm ci on the github machines instead (#16183)
|
há 3 meses atrás |
|
test-quantize-stats.cpp
|
ec18edfcba
server: introduce API for serving / loading / unloading multiple models (#17470)
|
há 1 mês atrás |
|
test-regex-partial.cpp
|
3198405e98
`common`: add partial regex support (#12808)
|
há 8 meses atrás |
|
test-rope.cpp
|
73460f6278
ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805)
|
há 2 meses atrás |
|
test-sampling.cpp
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
há 4 meses atrás |
|
test-thread-safety.cpp
|
cd5e3b5754
server : support unified cache across slots (#16736)
|
há 2 meses atrás |
|
test-tokenizer-0.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
há 1 ano atrás |
|
test-tokenizer-0.py
|
6fbd432211
py : logging and flake8 suppression refactoring (#7081)
|
há 1 ano atrás |
|
test-tokenizer-0.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
há 6 meses atrás |
|
test-tokenizer-1-bpe.cpp
|
13b4548877
cmake : do not include ./src as public for libllama (#13062)
|
há 8 meses atrás |
|
test-tokenizer-1-spm.cpp
|
13b4548877
cmake : do not include ./src as public for libllama (#13062)
|
há 8 meses atrás |
|
test-tokenizer-random.py
|
70cd37dbbe
requirements : update transformers/torch for Embedding Gemma (#15828)
|
há 4 meses atrás |
|
test-tokenizers-repo.sh
|
624207e676
devops: add s390x & ppc64le CI (#15925)
|
há 3 meses atrás |
Xuan-Son Nguyen