Francis Couture-Harpin ba6f6be6ce imatrix : don't use FMA explicitly ...

This should make comparisons between the formats easier
because this matches the behavior of the previous version.

2025-06-18 16:33:37 -04:00

..

batched-bench

llama : deprecate llama_kv_self_ API (#14030)

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

cvector-generator

llama : deprecate llama_kv_self_ API (#14030)

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

export-lora

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

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

gguf-split

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

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

imatrix

imatrix : don't use FMA explicitly

2025-06-18 16:33:37 -04:00

llama-bench

llama : deprecate llama_kv_self_ API (#14030)

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

main

llama : deprecate llama_kv_self_ API (#14030)

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

mtmd

mtmd : refactor llava-uhd preprocessing logic (#14247)

2025-06-18 10:43:57 +02:00

perplexity

llama : deprecate llama_kv_self_ API (#14030)

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

quantize

Merge branch 'master' into compilade/imatrix-batched-chunks

2025-06-18 16:32:35 -04:00

rpc

rpc : Fix build on OpenBSD (#13541)

2025-05-25 15:35:53 +03:00

run

llama : deprecate llama_kv_self_ API (#14030)

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

server

server : fix incorrect usage of llama_get_embeddings() (#14225)

2025-06-16 22:33:27 +03:00

tokenize

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

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

tts

sync : vendor (#13901)

2025-05-30 16:25:45 +03:00

CMakeLists.txt

mtmd : rename llava directory to mtmd (#13311)

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