b6088

imatrix : warn when GGUF imatrix is saved without .gguf suffix (#15076)

* imatrix : add warning when suffix is not .gguf for GGUF imatrix

* imatrix : only warn about suffix when output format is unspecified

b6087

cmake: Add GGML_BACKEND_DIR option (#15074)

* cmake: Add GGML_BACKEND_DIR option

This can be used by distributions to specify where to look for backends
when ggml is built with GGML_BACKEND_DL=ON.

* Fix phrasing

b6085

model: support GLM 4.5 family of models (#14939)

* model: Add GLM 4.5 (#14921)

Co-authored-by: Sigbjørn Skjæret <[email protected]>

* Merge in PR suggestions

Co-authored-by: Sigbjørn Skjæret <[email protected]>

* model: Add GLM 4.5 family of models (#14921)

1. Updated tensor_mapping.py with NextN tensor mappings

- Added proper tensor mappings for all NextN/MTP tensors in /Users/samm/git/llama.cpp/gguf-py/gguf/tensor_mapping.py
- Added mappings for: eh_proj, embed_tokens, enorm, hnorm, shared_head.head, shared_head.norm

2. Added num_nextn_predict_layers configuration

- Added LLM_KV_NUM_NEXTN_PREDICT_LAYERS constant to llama-arch.h and llama-arch.cpp
- Added num_nextn_predict_layers field to llama_hparams struct
- Updated GLM4_MOE parameter loading in llama-model.cpp to read this parameter
- Modified tensor loading logic to conditionally load NextN tensors based on num_nextn_predict_layers
- Added GGUF writer support in gguf_writer.py with add_num_nextn_predict_layers() method
- Updated conversion script to extract and write this parameter from HuggingFace config

3. Added FIM tokens for GLM4_MOE

- Added GLM-4.5's FIM tokens to llama-vocab.cpp:
  - <|code_prefix|> for FIM_PRE
  - <|code_suffix|> for FIM_SUF
  - <|code_middle|> for FIM_MID

4. Removed manual NextN tensor handling

- Removed the special-case handling in convert_hf_to_gguf.py that manually mapped NextN tensors
- NextN tensors are now handled automatically through the proper tensor mapping system

* glm 4.5 update tensors names

* model: glm 4.5 apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <[email protected]>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <[email protected]>

* model: glm 4.5 apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <[email protected]>

* model: glm 4.5 apply suggestions from code review

* Apply suggestions from code review

* patch broken chat template

* typings fix

* add TENSOR_SKIP flag


Co-authored-by: Diego Devesa <[email protected]>

* Update src/llama-model-loader.h

Co-authored-by: Sigbjørn Skjæret <[email protected]>

---------

Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Diego Devesa <[email protected]>

b6084

quantize : fix confusing error message if ftype is invalid (#15071)

b6083

ggml: WebGPU backend host improvements and style fixing (#14978)

* Add parameter buffer pool, batching of submissions, refactor command building/submission

* Add header for linux builds

* Free staged parameter buffers at once

* Format with clang-format

* Fix thread-safe implementation

* Use device implicit synchronization

* Update workflow to use custom release

* Remove testing branch workflow

b6082

vulkan: fix build when using glslang that does not support coopmat2 (…

b6081

imatrix : use GGUF by default (#14842)

* imatrix : use GGUF by default

* imatrix : use GGUF regardless of the output filename

The legacy format can only be produced with --output-format dat

b6080

imatrix : fix 3d activation handling for hybrid and recurrent models …

b6079

memory : handle kv_unified for hybrid models (#15050)

b6078

vocab : JetBrains Mellum pre-tokenizer (#15045)