CUDA: fix bug in rms_norm fusion (#15660)

* CUDA: fix bug in rms_norm fusion

* Fix bug for OP_REPEAT

* Fix index for add

chat : Seed OSS thinking + tool call support (#15552)

* Reasoning and tool-calling support for Seed OSS

* Fix grammar and partial parsing

* Whitespace

* New chat template

* Update common/chat.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update common/chat.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Remove unused 'purge_healing_marker' helper

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

CUDA: fuse adds, fuse add with rms norm (#15631)

* CUDA: fused add with rms_norm_mul

* Non-broadcast fuse works

* Add fused adds

* format

* Remove n_fuse from template params

* Address review comments

* Move template inside binbcast

nvidia nemotron nano v2 (nemotronh) (#15507)

* feat: Add NEMOTRONH to python arch enum

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Add NEMOTRONH to c++ arch enum

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Add NEMOTRONH to llama-arch layer map

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: First pass at conversion for nemotronh

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Add a verbose log for each tensor loaded

This is really helpful for diagnosing mismatches between the expected and
received tensors

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: First (broken) pass at nemotronh model architecture

It generates tokens, just not valid ones!

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Explicitly enable add_bos_token during conversion

The `tokenizer.json`/`tokenizer_config.json` in the model are a bit
contradictory. In the config, add_bos_token is set to False, but the
tokenizer model itself has a post_processor that adds the BOS token via
type: TemplateProcessing

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Use relu2 (LLM_FFN_RELU_SQR) for activation in FFN layers

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Only allocate attention cache for attention layers (not non-recurrent)

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Move residual add to after every block

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Use the correct norm tensor for the MLP blocks

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* Nemotron-H: MLP gate cleanup (pass NULL for unused gate)

This model does not use a gate in MLP blocks; pass NULLs for gate tensors to make intent clear and avoid unused-pointer noise.

* SSM: respect ssm_dt_rank for dt_dim when provided

Use GGUF-provided time_step_rank (ssm_dt_rank) to set dt_dim when > 0; fallback to max(64, n_embd/16).

* fix: plamo2 - revert dt_dim to default (remove ssm_dt_rank usage)

* Rename nemotronh to nemotron_h for consistency

- Update architecture name from NEMOTRONH to NEMOTRON_H in constants.py
- Change architecture string from 'nemotronh' to 'nemotron_h' in all files
- Update enum LLM_ARCH_NEMOTRONH to LLM_ARCH_NEMOTRON_H
- Update class name llm_build_nemotronh to llm_build_nemotron_h
- Consistent naming with underscore convention (nemotron_h vs nemotronh)

* feat: Support conversion for older NemotronH models

https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409
Branch: gabe-l-hart/nvidia-nemotron-nano-15409

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Maicon Domingues <dominguesm@outlook.com>
Co-authored-by: weatherman <fxdstudios@gmail.com>

fix: Compute the full sum in llama-eval-callback, not just the sum of…

CUDA: add conv2d (#15635)

* CUDA: add conv2d

* CUDA: conv2d - correct formatting and added const

ggml-cpu: fix invalid hsum build in debug s390x (#15634)

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml : fix SSM_SCAN for n_groups > 1 (#15625)

kv-cache : fix find_slot to not search for continuous slot (#15638)

ggml-ci

model : jina-embeddings-v3 support (#13693)

* initial jina-embeddings-v3 support

* initial jina-embeddings-v3 support

* initial jina-embeddings-v3 support

* fix vocab parsing with only tokenizer.json

* set mask token lstrip attribute

* additional unk_token_id fallback just in case [no ci]

* revert vocab_size() change [no ci]

* merge tensor loading into general bert

* rope

* add lora embedding and loading (non-functional)

* export separate lora ggufs instead

* add adapter metadata api

* use std::string

* convert_hf_to_lora compatibility

* fix assert

* apply suggestions from review

* apply suggestion from review