vshmidt/llama.cpp: LLM inference in C/C++ | Gitverse

/

/

Обзор ДокументацияВойти

/

/

Аналитика

Безопасность

common/gemma4 : handle parsing edge cases (#21760)

4 месяца назад

tests : add unit test coverage for llama_tensor_get_type (#20112)

4 месяца назад

tests : add unit test coverage for llama_tensor_get_type (#20112)

4 месяца назад

libs : rename libcommon -> libllama-common (#21936)

4 месяца назад

export-graph-ops.cpp

tests: allow exporting graph ops from HF file without downloading weights (#21182)

4 месяца назад

ci : add model tests + script wrapper (#4586)

3 года назад

ci : add model tests + script wrapper (#4586)

3 года назад

gguf-model-data.cpp

tests : add unit test coverage for llama_tensor_get_type (#20112)

4 месяца назад

gguf-model-data.h

tests : add unit test coverage for llama_tensor_get_type (#20112)

4 месяца назад

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

5 месяцев назад

test-arg-parser.cpp

ci, tests : use cmake to download models and remove libcurl dependency (#18791)

7 месяцев назад

test-autorelease.cpp

docs : Minor cleanups (#19252)

6 месяцев назад

test-backend-ops.cpp

metal : add XIELU unary op (#20802)

4 месяца назад

test-backend-sampler.cpp

tests: enable kv_unified to prevent cuda oom error on rtx 2060 (#20645)

5 месяцев назад

test-barrier.cpp

Fix race conditions in threadpool when dealing with dynamic/frequent n_threads changes (#17748)

8 месяцев назад

ggml : remove kompute backend (#14501)

год назад

test-chat-auto-parser.cpp

common/parser: fix reasoning whitespace bugs + extra parser tests (#21085)

4 месяца назад

test-chat-peg-parser.cpp

common/parser: add proper reasoning tag prefill reading (#20424)

5 месяцев назад

test-chat-template.cpp

chat : add Granite 4.0 chat template with correct tool_call role mapping (#20804)

4 месяца назад

common/autoparser : allow space after tool call (#22073)

4 месяца назад

test-double-float.cpp

ggml : minor naming changes (#8433)

2 года назад

test-gbnf-validator.cpp

cmake : do not include ./src as public for libllama (#13062)

год назад

test-gguf-model-data.cpp

tests : add unit test coverage for llama_tensor_get_type (#20112)

4 месяца назад

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

5 месяцев назад

test-grammar-integration.cpp

common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604)

5 месяцев назад

test-grammar-llguidance.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

8 месяцев назад

test-grammar-parser.cpp

common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604)

5 месяцев назад

jinja : support ensure_ascii=true, string repetition and int/float self-filtering (#21623)

4 месяца назад

test-json-partial.cpp

common : handle unicode during partial json parsing (#16526)

10 месяцев назад

test-json-schema-to-grammar.cpp

tests : remove obsolete .mjs script (#21615)

4 месяца назад

test-llama-archs.cpp

mtmd: add Gemma 4 audio conformer encoder support (#21421)

4 месяца назад

test-llama-grammar.cpp

common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604)

5 месяцев назад

common : use common_ prefix for common library functions (#9805)

2 года назад

test-lora-conversion-inference.sh

cli: new CLI experience (#17824)

8 месяцев назад

test-model-load-cancel.cpp

llama : update llama_model API names (#11063)

2 года назад

test-mtmd-c-api.c

mtmd: add pos_0 to mtmd_image_tokens_get_decoder_pos (breaking change) (#22082)

4 месяца назад

tests : fix test-opt with GGML_BACKEND_DL (#15599)

год назад

test-peg-parser.cpp

Autoparser - complete refactoring of parser architecture (#18675)

5 месяцев назад

test-quant-type-selection.cpp

tests : add unit test coverage for llama_tensor_get_type (#20112)

4 месяца назад

test-quantize-fns.cpp

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

4 месяца назад

test-quantize-perf.cpp

ci: run the x64 and arm ci on the github machines instead (#16183)

год назад

test-quantize-stats.cpp

libs : rename libcommon -> libllama-common (#21936)

4 месяца назад

test-reasoning-budget.cpp

common : inhibit lazy grammar sampler while reasoning is active (#20970)

4 месяца назад

test-regex-partial.cpp

common/grammar : replace problematic backtracking regex `[\s\S]*` (#18342)

7 месяцев назад

ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805)

9 месяцев назад

test-sampling.cpp

sampling : optimize samplers by reusing bucket sort (#15665)

год назад

test-state-restore-fragmented.cpp

common : move up common_init() and fix Windows UTF-8 logs (#21176)

4 месяца назад

test-thread-safety.cpp

common : move up common_init() and fix Windows UTF-8 logs (#21176)

4 месяца назад

test-tokenizer-0.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

8 месяцев назад

test-tokenizer-0.py

requirements : update transformers to 5.5.1 (#21617)

4 месяца назад

test-tokenizer-0.sh

model : add Jina Embeddings v5 Nano (partial EuroBERT) support (#19826)

6 месяцев назад

test-tokenizer-1-bpe.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

8 месяцев назад

test-tokenizer-1-spm.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

8 месяцев назад

test-tokenizer-random.py

requirements : update transformers to 5.5.1 (#21617)

4 месяца назад

test-tokenizers-repo.sh

devops: add s390x & ppc64le CI (#15925)

год назад

common : implement new jinja template engine (#18462)

7 месяцев назад