Daniel Hiltgen 1fd1ccf7ad model: align Laguna with upstream llama.cpp (#17335) ...

Update llama.cpp to pick up upstream Laguna implementation and remove Ollama's local Laguna implementation. Retain a narrow Metal-only scaling workaround for routed-MoE prompt overflow.

Translate older Ollama GGUF attention-gate and SWA metadata names so existing models continue to load.

2026-07-22 17:09:18 -07:00

..

cogito_test.go

model/parsers: fix missing parallel tool call indices (#15467)

2026-04-10 15:23:21 -07:00

cogito.go

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

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

cohere_test.go

models: add cohere2_moe (Command A / North) to the MLX engine (#16670)

2026-06-16 23:15:21 -07:00

cohere.go

models: add cohere2_moe (Command A / North) to the MLX engine (#16670)

2026-06-16 23:15:21 -07:00

deepseek3_test.go

model/parsers: fix missing parallel tool call indices (#15467)

2026-04-10 15:23:21 -07:00

deepseek3.go

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

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

functiongemma_test.go

model/parsers: fix missing parallel tool call indices (#15467)

2026-04-10 15:23:21 -07:00

functiongemma.go

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

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

gemma4_test.go

model: align gemma4 chat template handling (#17182)

2026-07-14 15:42:04 -07:00

gemma4.go

model: align gemma4 chat template handling (#17182)

2026-07-14 15:42:04 -07:00

glm46_test.go

model/parsers: finalize incomplete GLM tool calls (#17250)

2026-07-22 13:53:47 -07:00

glm46.go

model/parsers: finalize incomplete GLM tool calls (#17250)

2026-07-22 13:53:47 -07:00

glm47_test.go

model/parsers: add stable tool call indexing for glm47 and qwen3 parsers (#14484)

2026-02-26 18:14:29 -08:00

glm47.go

model/parsers: add stable tool call indexing for glm47 and qwen3 parsers (#14484)

2026-02-26 18:14:29 -08:00

glmocr.go

Add GLM-OCR vision model support (#14024)

2026-02-02 15:39:18 -08:00

laguna_test.go

model: align Laguna with upstream llama.cpp (#17335)

2026-07-22 17:09:18 -07:00

laguna.go

model: add Laguna v8 chat support and fix Metal inference (#17291)

2026-07-21 16:06:29 -07:00

lfm2_test.go

model: update lfm2 parser/renderer for optional thinking (#16359)

2026-06-14 20:37:08 -07:00

lfm2.go

model: update lfm2 parser/renderer for optional thinking (#16359)

2026-06-14 20:37:08 -07:00

ministral_test.go

model/parsers: fix missing parallel tool call indices (#15467)

2026-04-10 15:23:21 -07:00

ministral.go

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

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

nemotron3nano_test.go

New models (#15861)

2026-04-28 11:50:12 -07:00

nemotron3nano.go

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

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

olmo3_test.go

model/parsers: fix missing parallel tool call indices (#15467)

2026-04-10 15:23:21 -07:00

olmo3_think_test.go

parsers/renderers: olmo3 think (#13290)

2025-12-09 10:41:47 -08:00

olmo3_think.go

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

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

olmo3.go

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

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

parsers_test.go

parser/renderer: add Ornith 9B renderer/parser support (#16920)

2026-06-25 23:18:47 -07:00

parsers.go

model: align Laguna with upstream llama.cpp (#17335)

2026-07-22 17:09:18 -07:00

qwen3_test.go

model/parsers: add stable tool call indexing for glm47 and qwen3 parsers (#14484)

2026-02-26 18:14:29 -08:00

qwen3.go

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

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

qwen3coder_test.go

model/parsers: add stable tool call indexing for glm47 and qwen3 parsers (#14484)

2026-02-26 18:14:29 -08:00

qwen3coder.go

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

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

qwen3vl_nonthinking_test.go

model/parsers: fix missing parallel tool call indices (#15467)

2026-04-10 15:23:21 -07:00

qwen3vl_thinking_test.go

model: fix qwen3 tool calling in thinking (#14477)

2026-02-26 16:13:18 -08:00

qwen3vl.go

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

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

qwen35_test.go

parsers: qwen3.5 streaming tool-call parsing and add regression test (#15098)

2026-03-27 14:04:14 -07:00

qwen35.go

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

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

testhelpers_test.go

model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)

2026-01-19 12:47:17 -08:00