]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
kv-cache : extend cache quantization checks (#21586)
authorErik Scholz <redacted>
Wed, 8 Apr 2026 13:08:57 +0000 (15:08 +0200)
committerGitHub <redacted>
Wed, 8 Apr 2026 13:08:57 +0000 (16:08 +0300)
commit3ba12fed0a50af94bd9cfdea6f0b59e5aba8ed4a
tree86d03ea5346cea6d7a5c891958feaa98d1044c8d
parent54739490707d4838630887a666f124c0a60003bb
kv-cache : extend cache quantization checks (#21586)

to also check for enabled flash attention, instead of just auto.
src/llama-context.cpp