Devon Rifkin 7c94471d38 ggml: more accurate estimates for head count array case ...

Also standardized the approach by always treatting `HeadCount()` and
`HeadCountKV()` as arrays by filling them with the same value when
they're a scalar in the original GGUF

2025-04-10 16:28:34 -07:00

..

llm_darwin.go

Optimize container images for startup (#6547)

2024-09-12 12:10:30 -07:00

llm_linux.go

Optimize container images for startup (#6547)

2024-09-12 12:10:30 -07:00

llm_windows.go

runner: Set windows above normal priority (#6905)

2024-09-21 16:54:49 -07:00

memory_test.go

ggml: Support heterogeneous KV cache layer sizes in memory estimation

2025-03-26 13:16:03 -07:00

memory.go

ggml: more accurate estimates for head count array case

2025-04-10 16:28:34 -07:00

server_test.go

llm: do not error on "null" format (#8139)

2024-12-17 09:49:37 -08:00

server.go

llm: set done reason at server level (#9830)

2025-04-03 10:19:24 -07:00

status.go

Improve crash reporting (#7728)

2024-11-19 16:26:57 -08:00