Files in llamaR

Interface for Large Language Models via 'llama.cpp'

configure

MD5

NEWS.md README.md

NAMESPACE

DESCRIPTION

LICENSE

configure.win

cleanup

R/hf.R R/llama.R R/llamaR-package.R R/chat.R R/embed.R R/serve.R

src/llama-vocab.h

src/llama-cparams.h

src/Makevars.win

src/unicode-data.h

src/llama-kv-cache-iswa.h

src/llama-adapter.h

src/llama-model-loader.cpp

src/llama-memory-hybrid.h

src/llama-model.cpp

src/llama-grammar.h

src/llama-sampling.h

src/llama.cpp

src/llama-memory-hybrid.cpp

src/llama-model.h

src/llama-impl.cpp

src/llama-kv-cache-iswa.cpp

src/llama-chat.h

src/unicode.cpp

src/llama-model-loader.h

src/llama-hparams.h

src/llama-quant.cpp

src/llama-sampling.cpp

src/llama-memory-recurrent.cpp

src/llama-cpp.h

src/llama-memory.cpp

src/llama-kv-cells.h

src/r_llama_interface.cpp

src/llama-impl.h

src/llama-memory-recurrent.h

src/unicode.h

src/llama-graph.cpp

src/llama-grammar.cpp

src/llama-chat.cpp

src/llama-vocab.cpp

src/llama.h

src/llama-memory-hybrid-iswa.h

src/llama-memory.h

src/llama-model-saver.h

src/Makevars.win.in

src/llama-batch.cpp

src/llama-cparams.cpp

src/Makevars.in

src/llama-mmap.cpp

src/llama-kv-cache.h

src/llama-context.h

src/unicode-data.cpp

src/llama-kv-cache.cpp

src/llama-context.cpp

src/llama-io.cpp

src/r_llama_compat.h

src/llama-model-saver.cpp

src/llama-io.h

src/llama-arch.cpp

src/llama-adapter.cpp

src/llama-quant.h

src/llama-mmap.h

src/llama-memory-hybrid-iswa.cpp

src/llama-hparams.cpp

src/llama-arch.h

src/llama-batch.h

src/llama-graph.h

src/models/seed-oss.cpp

src/models/rwkv7-base.cpp

src/models/qwen3vl-moe.cpp

src/models/chameleon.cpp

src/models/rnd1.cpp

src/models/exaone-moe.cpp

src/models/hunyuan-moe.cpp

src/models/deepseek2.cpp

src/models/gemma-embedding.cpp

src/models/cohere2-iswa.cpp

src/models/nemotron-h.cpp

src/models/dream.cpp

src/models/t5-enc.cpp

src/models/rwkv6.cpp

src/models/qwen3moe.cpp

src/models/deepseek.cpp

src/models/llama.cpp

src/models/modern-bert.cpp

src/models/models.h

src/models/dots1.cpp

src/models/mimo2-iswa.cpp

src/models/falcon-h1.cpp

src/models/glm4-moe.cpp

src/models/wavtokenizer-dec.cpp

src/models/gemma.cpp

src/models/jamba.cpp

src/models/neo-bert.cpp

src/models/rwkv6-base.cpp

src/models/phi2.cpp

src/models/xverse.cpp

src/models/qwen3next.cpp

src/models/bitnet.cpp

src/models/openelm.cpp

src/models/minimax-m2.cpp

src/models/olmo.cpp

src/models/mpt.cpp

src/models/qwen2.cpp

src/models/llama-iswa.cpp

src/models/phi3.cpp

src/models/gemma2-iswa.cpp

src/models/qwen.cpp

src/models/arwkv7.cpp

src/models/codeshell.cpp

src/models/jais.cpp

src/models/grovemoe.cpp

src/models/rwkv7.cpp

src/models/llada.cpp

src/models/plamo.cpp

src/models/ernie4-5.cpp

src/models/smollm3.cpp

src/models/nemotron.cpp

src/models/bailingmoe.cpp

src/models/starcoder2.cpp

src/models/exaone.cpp

src/models/stablelm.cpp

src/models/refact.cpp

src/models/qwen2vl.cpp

src/models/cogvlm.cpp

src/models/qwen3.cpp

src/models/orion.cpp

src/models/gpt2.cpp

src/models/apertus.cpp

src/models/qwen2moe.cpp

src/models/lfm2.cpp

src/models/olmoe.cpp

src/models/granite-hybrid.cpp

src/models/olmo2.cpp

src/models/falcon.cpp

src/models/bloom.cpp

src/models/grok.cpp

src/models/dbrx.cpp

src/models/baichuan.cpp

src/models/bailingmoe2.cpp

src/models/ernie4-5-moe.cpp

src/models/exaone4.cpp

src/models/gemma3n-iswa.cpp

src/models/afmoe.cpp

src/models/gemma3.cpp

src/models/pangu-embedded.cpp

src/models/plm.cpp

src/models/rwkv6qwen2.cpp

src/models/plamo3.cpp

src/models/glm4.cpp

src/models/maincoder.cpp

src/models/chatglm.cpp

src/models/gptneox.cpp

src/models/command-r.cpp

src/models/arcee.cpp

src/models/llada-moe.cpp

src/models/mamba.cpp

src/models/starcoder.cpp

src/models/internlm2.cpp

src/models/granite.cpp

src/models/smallthinker.cpp

src/models/plamo2.cpp

src/models/qwen3vl.cpp

src/models/openai-moe-iswa.cpp

src/models/graph-context-mamba.cpp

src/models/t5-dec.cpp

src/models/hunyuan-dense.cpp

src/models/minicpm3.cpp

src/models/bert.cpp

src/models/arctic.cpp

src/models/mistral3.cpp

src/models/deci.cpp

inst/doc/chat-and-agents.html

inst/doc/chat-and-agents.Rmd

inst/doc/getting-started.html

inst/doc/getting-started.Rmd

inst/examples/opencode.json

inst/examples/chat.R inst/examples/serve_openai.R inst/scripts/example_advanced.R inst/scripts/diag_graph_reuse.R inst/scripts/bench_batch.R inst/scripts/diag_splits.R inst/scripts/profile_vs_llamacpp.R inst/scripts/benchmark_compare.R inst/scripts/diag_offload_profile.R inst/scripts/benchmark.R

inst/scripts/profile_vs_llamacpp.sh

inst/scripts/profile_gpu.R inst/scripts/test_batch.R inst/scripts/test.R

build/vignette.rds

tests/testthat.R tests/testthat/test-hf.R tests/testthat/test-serve.R tests/testthat/test-chat.R tests/testthat/test-basic.R vignettes/chat-and-agents.Rmd vignettes/getting-started.Rmd man/llama_hf_download.Rd man/llama_numa_init.Rd man/llama_chat_apply_template.Rd man/llama_hf_cache_dir.Rd man/llama_supports_rpc.Rd man/llama_get_embeddings_ith.Rd man/llama_supports_mmap.Rd man/chat_llamar_stop.Rd man/llama_generate.Rd man/llama_state_save.Rd man/llama_vocab_is_eog.Rd man/llama_n_ctx_seq.Rd man/llama_perf.Rd man/llamaR-package.Rd man/llama_set_causal_attn.Rd man/llama_get_verbosity.Rd man/llama_state_get_size.Rd man/llama_token_to_piece.Rd man/llama_lora_apply.Rd man/llama_time_us.Rd man/llama_memory_seq_cp.Rd man/llama_detokenize.Rd man/llama_n_batch.Rd man/llama_free_model.Rd man/llama_chat_builtin_templates.Rd man/llama_batch_free.Rd man/embed_llamar.Rd man/llama_get_embeddings_seq.Rd man/llama_lora_load.Rd man/llama_max_devices.Rd man/llama_memory_breakdown_print.Rd man/llama_get_logits.Rd man/llama_perf_reset.Rd man/llama_perf_print.Rd man/llama_n_seq_max.Rd man/llama_vocab_info.Rd man/llama_n_ctx.Rd man/llama_get_logits_ith.Rd man/llama_memory_seq_div.Rd man/llama_n_threads.Rd man/llama_n_threads_batch.Rd man/llama_n_ubatch.Rd man/llama_set_threads.Rd man/llama_set_abort_callback.Rd man/llama_memory_seq_pos_range.Rd man/llama_model_meta_val.Rd man/llama_supports_gpu.Rd man/llama_load_model_hf.Rd man/llama_synchronize.Rd man/llama_vocab_is_control.Rd man/llama_get_embeddings.Rd man/llama_hf_list.Rd man/llama_memory_seq_add.Rd man/llama_hf_cache_info.Rd man/llama_chat_template.Rd man/llama_serve_openai.Rd man/llama_pooling_type.Rd man/llama_encode.Rd man/llama_get_model.Rd man/llama_lora_remove.Rd man/llama_embed_batch.Rd man/llama_gen_begin.Rd man/llama_lora_clear.Rd man/llama_memory_seq_keep.Rd man/llama_model_meta.Rd man/llama_free_context.Rd man/llama_memory_can_shift.Rd man/llama_vocab_get_score.Rd man/llama_vocab_get_text.Rd man/llama_hf_cache_clear.Rd man/llama_load_model.Rd man/chat_llamar.Rd man/llama_backend_devices.Rd man/llama_memory_clear.Rd man/llama_vocab_type.Rd man/llama_set_verbosity.Rd man/llama_embeddings.Rd man/llama_tokenize.Rd man/llama_gen_next.Rd man/llama_supports_mlock.Rd man/llama_set_warmup.Rd man/llama_system_info.Rd man/llama_state_load.Rd man/llama_generate_batch.Rd man/llama_memory_seq_rm.Rd man/llama_new_context.Rd man/llama_batch_init.Rd man/llama_model_info.Rd man/llama_gen_end.Rd

llamaR documentation built on May 28, 2026, 1:06 a.m.