; ------------------------------------------------------------------------------
; FILE: roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2
; DESCRIPTION: llama.cpp --models-preset INI for llama-server-router.
;
; Purpose: define all router-served GGUFs as named model entries so that:
;   - Each model is explicitly named and configured (no auto-discovery surprises)
;   - Aliases can be added per model (impossible with --models-dir alone)
;   - The Phi-3.5-mini-instruct-Q8_0 entry carries the alias
;     "Phi-3.5-mini-instruct-8bit" — Ryan's Hermes auxiliary.title_generation
;     already references this friendlier name; both names resolve to the same
;     GGUF child process.
;
; INI format notes (llama.cpp preset.md):
;   - Section header (e.g. [Phi-3.5-mini-instruct-Q8_0]) is the primary model ID
;     that appears in /v1/models and that clients send in the "model" field.
;   - `alias` adds an ADDITIONAL name — both the section name and the alias work.
;   - The `model` key is the absolute path to the GGUF file.
;   - All other keys map directly to llama-server CLI flags (underscores or hyphens).
;
; Known upstream issues (Aug 2026):
;   - GH #22364: --models-preset creates an extra "default" model entry in
;     /v1/models. This is cosmetic — it has no functional effect on model
;     selection by name. Document and move on.
;   - GH #23460: can't pass per-model samplers via --models-preset in router
;     mode. Non-issue: Hermes always sends sampling params in the request body.
;
; Added 2026-08-12 (t_9adf0889): Phi alias — War Machine.
; All per-model settings carry over unchanged from the --models-dir baseline
; (ctx_size=65536, n_gpu_layers=99, cache=q4_0 for both K and V, models-max=4).
; ------------------------------------------------------------------------------

; --- Production model: Qwen3.6-35B-A3B-UD-Q4_K_S ----------------------------
; Primary model ID: Qwen3.6-35B-A3B-UD-Q4_K_S (unchanged from --models-dir)
; ~20GB, primary Hermes production LLM. Context: 64K with q4_0 KV cache.
[Qwen3.6-35B-A3B-UD-Q4_K_S]
model        = {{ llm_models_dir }}/Qwen3.6-35B-A3B-UD-Q4_K_S.gguf
n-gpu-layers = {{ llm_router_gpu_layers }}
ctx-size     = {{ llm_router_ctx_size }}
cache-type-k = {{ llm_router_cache_type_k }}
cache-type-v = {{ llm_router_cache_type_v }}
batch-size   = {{ llm_router_batch_size }}
ubatch-size  = {{ llm_router_ubatch_size }}
parallel     = {{ llm_router_parallel }}

; --- Auxiliary model: Phi-3.5-mini-instruct-Q8_0 ----------------------------
; Primary model ID: Phi-3.5-mini-instruct-Q8_0 (unchanged from --models-dir)
; Alias:            Phi-3.5-mini-instruct-8bit (NEW — Ryan's config target)
; Both names resolve to this GGUF child process.
; ~3.8GB, auxiliary.title_generation consumer in Ryan's Hermes config.
; The alias is what this entire task is about — once deployed, the
; "Auxiliary title generation failed" warning will be gone.
[Phi-3.5-mini-instruct-Q8_0]
model        = {{ llm_models_dir }}/Phi-3.5-mini-instruct-Q8_0.gguf
alias        = Phi-3.5-mini-instruct-8bit
n-gpu-layers = {{ llm_router_gpu_layers }}
ctx-size     = {{ llm_router_ctx_size }}
cache-type-k = {{ llm_router_cache_type_k }}
cache-type-v = {{ llm_router_cache_type_v }}
batch-size   = {{ llm_router_batch_size }}
ubatch-size  = {{ llm_router_ubatch_size }}
parallel     = {{ llm_router_parallel }}

; --- Auxiliary model: Meta-Llama-3.1-8B-Instruct-Q4_K_M --------------------
; Primary model ID: Meta-Llama-3.1-8B-Instruct-Q4_K_M (unchanged)
; ~4.6GB, general-purpose small model.
[Meta-Llama-3.1-8B-Instruct-Q4_K_M]
model        = {{ llm_models_dir }}/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
n-gpu-layers = {{ llm_router_gpu_layers }}
ctx-size     = {{ llm_router_ctx_size }}
cache-type-k = {{ llm_router_cache_type_k }}
cache-type-v = {{ llm_router_cache_type_v }}
batch-size   = {{ llm_router_batch_size }}
ubatch-size  = {{ llm_router_ubatch_size }}
parallel     = {{ llm_router_parallel }}