ddh0 a68f31edd7 fix KLD percentile output (#15999) ...

In `llama-perplexity`, when using `--kl-divergence`, the KL divergence statistics output mistakenly displays the 99th percentile twice. This change fixes that and correctly displays the 90th percentile as originally intended (presumably).

2025-09-15 09:54:57 +02:00

..

batched-bench

batched-bench : fix llama_synchronize usage during prompt processing (#15835)

2025-09-08 10:27:07 +03:00

cvector-generator

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

export-lora

mtmd : fix 32-bit narrowing issue in export-lora and mtmd clip (#14503)

2025-07-25 13:08:04 +02:00

gguf-split

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

imatrix

imatrix : warn when GGUF imatrix is saved without .gguf suffix (#15076)

2025-08-04 23:26:52 +02:00

llama-bench

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

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

main

doc : update documentation for --tensor-split (#15980)

2025-09-14 12:10:07 +03:00

mtmd

llama : allow using iGPUs with --device (#15951)

2025-09-13 16:49:49 +02:00

perplexity

fix KLD percentile output (#15999)

2025-09-15 09:54:57 +02:00

quantize

llama : add gpt-oss (#15091)

2025-08-05 22:10:36 +03:00

rpc

rpc : fix regression when --device is used (#15981)

2025-09-14 12:28:18 +03:00

run

cmake : do not search for curl libraries by ourselves (#14613)

2025-07-10 15:29:05 +03:00

server

server : only attempt to enable thinking if using jinja (#15967)

2025-09-14 21:17:04 +02:00

tokenize

llama : move end-user examples to tools directory (#13249)

2025-05-02 20:27:13 +02:00

tts

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

2025-08-31 20:41:02 +03:00

CMakeLists.txt

mtmd : rename llava directory to mtmd (#13311)

2025-05-05 16:02:55 +02:00