Parafee41 f8a48df24d llm: decouple prompt caching from context shift (#16639) ...

This PR separates prompt caching from the public shift request option for native llama-server requests.

Previously, shift controlled two different mechanisms:

context shifting / overflow behavior
per-request llama-server cache_prompt
That meant callers could not request shift: false without also disabling prompt caching.

Fixes #16635

2026-06-11 16:05:24 -07:00

..

exit_status_other.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

exit_status_windows.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

exit_status.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

llama_binary_test.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

llama_binary.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

llama_server_test.go

llama-server: allow GPU offload for projectors (#16473)

2026-06-03 13:58:40 -07:00

llama_server.go

llm: decouple prompt caching from context shift (#16639)

2026-06-11 16:05:24 -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

win: lint fix (#10571)

2025-05-05 11:08:12 -07:00

media.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

metal_retry.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

rocm_default.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

rocm_windows.go

llama-server followups (#16353)

2026-06-01 10:44:21 -07:00

server_wait_test.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

server.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

status_test.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

status.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

vulkan_windows.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00