Georgi Gerganov 7956bb4d7f bench : cache the llama_context state at computed depth (#16944) ...

* bench : cache llama_context state at depth

* cont : handle failures to restore the old state

* cont : print information when the state is being reused

2025-11-07 21:23:11 +02:00

..

batched-bench

scripts : add script to bench models (#16894)

2025-11-02 00:15:31 +02:00

cvector-generator

…

export-lora

…

gguf-split

ci : use smaller model (#16168)

2025-09-22 09:11:39 +03:00

imatrix

Manually link -lbsd to resolve flock symbol on AIX (#16610)

2025-10-23 19:37:31 +08:00

llama-bench

bench : cache the llama_context state at computed depth (#16944)

2025-11-07 21:23:11 +02:00

main

llama-cli: prevent spurious assistant token (#16202)

2025-09-29 10:03:12 +03:00

mtmd

hparams : add n_embd_inp() to support extended embed (#16928)

2025-11-07 19:27:58 +01:00

perplexity

perplexity : show more kl-divergence data (#16321)

2025-09-29 09:30:45 +03:00

quantize

ci : use smaller model (#16168)

2025-09-22 09:11:39 +03:00

rpc

rpc : report actual free memory (#16616)

2025-10-17 18:02:52 +03:00

run

Manually link -lbsd to resolve flock symbol on AIX (#16610)

2025-10-23 19:37:31 +08:00

server

kv-cache : pad the cache size to 256 for performance (#17046)

2025-11-07 20:03:25 +02:00

tokenize

…

tts

model : Apertus model implementation (#15852)

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

CMakeLists.txt

…