Georgi Gerganov d00cbea63c server : host-memory prompt caching (#16391) ...

* minor : code style

* server : fix prompt similarity calculation

* server : initial host-memory prompt caching

* cont

* server : refactor

* cont

* cont : make the server task of the slot const

* cont : minor [no ci]

* server : cache prompts and checkpoints only for completion tasks

* server : improve prompt caching logic

* cont : fix check for number of cached prompts [no ci]

* server : improve caching logic, add -cram CLI arg

* server : print prompt mismatch info

* cont : better naming [no ci]

* server : improve prompt cache loading logic

* server : add option to debug the slot contents (#16482)

* server : add option to debug the slot contents

* Update tools/server/server.cpp

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

* server : add option to disable prompt cache

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

2025-10-09 18:54:51 +03:00

..

CMakeLists.txt

kv-cache : drop the "unified" prefix (#15467)

2025-08-21 17:00:33 +03:00

llama-adapter.cpp

aLoRA Support (#15327)

2025-09-05 17:32:39 -06:00

llama-adapter.h

aLoRA Support (#15327)

2025-09-05 17:32:39 -06:00

llama-arch.cpp

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-arch.h

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-batch.cpp

perplexity : provide a helpful hint for has_cpl case in split_equal error. (#15304)

2025-08-14 14:03:30 +03:00

llama-batch.h

llama : reuse compute graphs (#14482)

2025-07-17 19:08:33 +03:00

llama-chat.cpp

chat : Granite Docling stopping (#16438)

2025-10-06 18:59:40 +02:00

llama-chat.h

model : add grok-2 support (#15539)

2025-09-14 23:00:59 +02:00

llama-context.cpp

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-context.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-cparams.cpp

cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)

2025-06-15 10:08:58 +03:00

llama-cparams.h

llama : bump max seq limit from 64 to 256 (#15916)

2025-09-18 12:47:56 +03:00

llama-grammar.cpp

server: streaming of tool calls and thoughts when --jinja is on (#12379)

2025-05-25 01:48:08 +01:00

llama-grammar.h

tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)

2025-03-05 13:05:13 +00:00

llama-graph.cpp

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-graph.h

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-hparams.cpp

kv-cache : fix SWA checks + disable cacheless iSWA (#15811)

2025-09-05 10:39:22 +03:00

llama-hparams.h

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-impl.cpp

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

llama-impl.h

llama: use FA + max. GPU layers by default (#15434)

2025-08-30 16:32:10 +02:00

llama-io.cpp

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama-io.h

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama-kv-cache-iswa.cpp

server : context checkpointing for hybrid and recurrent models (#16382)

2025-10-03 21:34:51 +03:00

llama-kv-cache-iswa.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-kv-cache.cpp

server : host-memory prompt caching (#16391)

2025-10-09 18:54:51 +03:00

llama-kv-cache.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-kv-cells.h

llama : remove KV cache defragmentation logic (#15473)

2025-08-22 12:22:13 +03:00

llama-memory-hybrid.cpp

memory : use sequential equal splits for recurrent modules (#16442)

2025-10-07 08:24:17 +03:00

llama-memory-hybrid.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-memory-recurrent.cpp

server : improve context checkpoint logic (#16440)

2025-10-08 10:57:29 +03:00

llama-memory-recurrent.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-memory.cpp

memory : correctly handle failure in apply() (#14438)

2025-06-30 18:03:03 +03:00

llama-memory.h

llama: print memory breakdown on exit (#15860)

2025-09-24 16:53:48 +02:00

llama-mmap.cpp

llama : allow using mmap without PrefetchVirtualMemory, apply GGML_WIN_VER to llama.cpp sources (#14013)

2025-06-05 11:57:42 +02:00

llama-mmap.h

llama-mmap: fix missing include (#11796)

2025-02-10 20:58:18 +02:00

llama-model-loader.cpp

model : Apertus model implementation (#15852)

2025-10-02 20:43:22 +03:00

llama-model-loader.h

model: support GLM 4.5 family of models (#14939)

2025-08-04 20:29:25 +02:00

llama-model-saver.cpp

llama : improve sep token handling (#14272)

2025-06-20 14:04:09 +02:00

llama-model-saver.h

llama/ggml: add LLM training support (#10544)

2025-05-12 14:44:49 +02:00

llama-model.cpp

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-model.h

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

2025-10-09 09:39:18 +03:00

llama-quant.cpp

llama-quant : fix the verification of attention layers for encoder-decoder models (#16023)

2025-09-17 09:30:55 +02:00

llama-quant.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-sampling.cpp

sampling : optimize dist sampler (#15704)

2025-09-03 18:16:26 +03:00

llama-sampling.h

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

llama-vocab.cpp

model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)

2025-10-05 14:57:47 +02:00

llama-vocab.h

model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)

2025-10-05 14:57:47 +02:00

llama.cpp

ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (#15797)

2025-09-11 22:47:38 +02:00

unicode-data.cpp

server : better security control for public deployments (#9776)

2024-10-08 13:27:04 +02:00

unicode-data.h

llama : reduce compile time and binary size (#9712)

2024-10-02 15:49:55 +02:00

unicode.cpp

model : add Kimi-K2 support (#14654)

2025-07-15 21:54:22 +02:00

unicode.h

devops: add s390x & ppc64le CI (#15925)

2025-09-27 02:03:33 +08:00