homelab/ansible/roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2

; ------------------------------------------------------------------------------
; 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).
;
; UPDATED (t_ryan_per_model_ctx, per Ryan/JARVIS request): Llama-3.1-8B and
; Phi-3.5-mini now get PER-MODEL ctx-size/flash-attn matched to actual
; workload instead of the uniform 65536 used by every model previously:
;   - Llama-3.1-8B-Instruct-Q4_K_M: ctx-size 8192  (tool-routing/micro-tasks)
;   - Phi-3.5-mini-instruct-Q8_0:   ctx-size 32768 (long web scrapes/logs)
; Both now request explicit flash-attn=true (was "auto"). Qwen3.6-35B is
; INTENTIONALLY left untouched at ctx-size 65536 / flash-attn auto — not part
; of this change. Existing aliases (Meta-Llama-3.1-8B-Instruct-4bit,
; Phi-3.5-mini-instruct-8bit) are PRESERVED unchanged to avoid breaking live
; Hermes custom_providers routing — see role README / deployment report for
; the alias-naming ambiguity flag (Ryan's pasted TOML used different alias
; strings: "llama-3.1-8b" / "phi-3.5-mini").
; ------------------------------------------------------------------------------

; --- 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 deployed — "model not found" errors are resolved.
;
; KNOWN ISSUE (2026-08-12, t_9adf0889):
;   json_schema response_format fails for Phi-3.5-mini in llama.cpp router
;   mode due to chat template grammar sampler incompatibility (GH #23460).
;   The grammar sampler generates root ::= "assistant|>\n" ... which fails
;   to initialize. This means Hermes auxiliary.title_generation still errors
;   with "HTTP 400: Failed to initialize samplers" when json_schema format
;   is requested. Without response_format (plain text), Phi works fine.
;
;   Resolution options:
;   a) Update auxiliary.title_generation.model in ~/.hermes/config.yaml to
;      Meta-Llama-3.1-8B-Instruct-Q4_K_M (which supports json_schema) — Ryan
;      needs to approve this config.yaml write (protected file).
;   b) Rebuild llama.cpp from a newer commit if this bug is fixed upstream.
;   c) Accept title generation degradation for Phi-specific structured output.
[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_phi_ctx_size }}
flash-attn   = {{ llm_router_phi_flash_attn }}
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 from --models-dir)
; Alias:            Meta-Llama-3.1-8B-Instruct-4bit (NEW — friendlier name)
; Both names resolve to this GGUF child process.
; ~4.6GB, general-purpose small model. Works with json_schema structured output.
[Meta-Llama-3.1-8B-Instruct-Q4_K_M]
model        = {{ llm_models_dir }}/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
alias        = Meta-Llama-3.1-8B-Instruct-4bit
n-gpu-layers = {{ llm_router_gpu_layers }}
ctx-size     = {{ llm_router_llama_ctx_size }}
flash-attn   = {{ llm_router_llama_flash_attn }}
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 }}

; --- Coder model: Qwen2.5-Coder-14B-Instruct-Q4_K_M -------------------------
; Primary model ID: Qwen2.5-Coder-14B-Instruct-Q4_K_M (filename-derived)
; Alias:            Qwen2.5-Coder-14B-Instruct-4bit (friendlier name)
; Both names resolve to this GGUF child process.
; ~8.4GB weights + ~0.6GB KV @ 16K ctx = ~9.0GB VRAM.
; ctx-size=16384, flash-attn=true per task t_55c164f5 / Ryan's request.
; Source: bartowski/Qwen2.5-Coder-14B-Instruct-GGUF (public, no auth)
; Added 2026-08-13 (t_55c164f5) — War Machine.
[Qwen2.5-Coder-14B-Instruct-Q4_K_M]
model        = {{ llm_models_dir }}/Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf
alias        = Qwen2.5-Coder-14B-Instruct-4bit
n-gpu-layers = {{ llm_router_gpu_layers }}
ctx-size     = {{ llm_router_coder_ctx_size }}
flash-attn   = {{ llm_router_coder_flash_attn }}
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 }}