AesSedai [Wed, 11 Feb 2026 15:47:30 +0000 (07:47 -0800)]
model: Add Kimi-K2.5 support (#19170)
* Move dequant_model to after the text_config merge
Add new kimi-k2.5 keys to mtmd convert
Update V_MMPROJ tensor mapping for new mm_projector.proj keys
Update V_M_IMP_NORM for new mm_projector.pre_norm key
* Fix a couple of oversights
* Add image support for Kimi-K2.5
* Revert changes to KimiVLForConditionalGeneration
* Fix an assert crash
* Fix permute swapping w / h on accident
* Kimi-K2.5: Use merged QKV for vision
* Kimi-K2.5: pre-convert vision QK to use build_rope_2d
* Kimi-K2.5: support non-interleaved rope for vision
Daniel Bevenius [Wed, 11 Feb 2026 04:38:13 +0000 (05:38 +0100)]
llama : refactor sampling_info to use buffer_view template (#19368)
* llama : refactor sampling_info to use buffer_view template
This commit updates the sampling_info struct in llama-context to use a
buffer_view template for the logits, probs, sampled tokens, and
candidates buffers.
The motivation for this is to simplify the code, improve type safety
and readability.
Oliver Simons [Tue, 10 Feb 2026 21:31:19 +0000 (22:31 +0100)]
CUDA : Update CCCL-tag for 3.2 to final release from RC (#19486)
CCCL 3.2 has been released since it was added to llama.cpp as part of
the backend-sampling PR, and it makes sense to update from RC to final
released version.
k4ss4n [Tue, 10 Feb 2026 09:57:48 +0000 (10:57 +0100)]
ggml : use noexcept overload for is_regular_file in backend registration (#19452)
using noexcept std::filesystem::directory_entry::is_regular_file
overload prevents abnormal termination upon throwing an error
(as caused by symlinks to non-existent folders on linux)
hipudding [Tue, 10 Feb 2026 06:18:59 +0000 (14:18 +0800)]
CANN: implement quantized MUL_MAT_ID for MoE models (#19228)
Implement ggml_cann_mul_mat_id_quant function to support quantized matrix
multiplication for Mixture of Experts (MoE) architectures on CANN backend.
Key features:
- Support Q4_0 and Q8_0 quantized weight formats
- Use IndexSelect to dynamically route expert-specific weights based on indices
- Leverage WeightQuantBatchMatmulV2 for efficient quantized computation
- Handle automatic F16 type conversion for hardware compatibility
- Support both per-expert and broadcast input modes
Implementation details:
- Extract expert weights and scales using CANN IndexSelect operation
- Process each batch and expert combination independently
- Create proper tensor views with correct stride for matmul operations
- Automatic input/output type casting to/from F16 as needed
Testing: All test cases passed for supported types (F32, F16, Q4_0, Q8_0).
Alex Trotta [Fri, 6 Feb 2026 20:05:19 +0000 (15:05 -0500)]
gguf-py : bump sentencepiece version (#19319)
* gguf-py: Bump sentencepiece version
There's a new version that's been out for a while that addresses the issues mentioned in https://github.com/ggml-org/llama.cpp/pull/14200. There's a long chain of reasons I would like this change, but the short version is that it allows people who use both `sentencepiece` and `gguf` to take advantage of these fixes. On conda-forge, currently, it locks the version (since there is no notion of optional dependencies).
Regardless, I don't think this should be too controversial.
ymcki [Fri, 6 Feb 2026 10:39:58 +0000 (18:39 +0800)]
Kimi-Linear support (backend agnostic + MLA KV cache) (#18755)
* kimi linear model implementation
* kimi linear convert_hf_to_gguf
* kimi linear constants.py tensor_mapping.py
* Kimi Linear ggml.h
* kimi linear ggml-cpu
* Kimi Linear ggml-cuda
* Kimi Linear ggml.c
* kimi linear src/llama
* remove "const int64_t n_seq_tokens = q->ne[2];" to get rid of unused variable warning
* remove type mismatch warning
* read MoE params
* removed some hard coded code
* removed all hard code
* use DeepseekV2 tokenizer
* removed unnecessary internal methods called by the old set_vocab of KimiLinear
* rewrite get_vocab for KimiLinear. Removed all kda_scan code
* removed all traces of kda_scan
* reduce OP count by 1 due to removal of kda_scan
* Move KIMI_LINEAR to llm_arch_is_hybrid to enable KV cache
* set n_embd_head_k/v to ensure kv cache works
* don't quantize conv1d of Kimi Linear
* Kimi Linear backend agnostic
* removed LOG_INFO
* naive chunking form implemented
* fixed some comments
* add Kimi-K2 specific tokens to be recognized as EOG
* build_kda_autoregressive is implemented to replace build_kda_recurrent for faster inference. sync'd to b7682
* replaced Akk and Aqk with mul_mat and clamp
* no clamp version
* Moved Aqk computation out of the loop
* fixed typo and split wkv_b into wk_b and wv_b
* MLA KV cache support
* fix trailing spaces
* moved const llama_model & model; around to follow qwen3next format and see if it cna pass the -Wunused-private-field error
* fix trailing whitespace
* removed traling whitespaces in empty line + make sure indentation is multiple of 4
* try to make lint happy
* remove blank lines to make lint happy
* removed at least blank line containing white space
* fixed flake8 complaints locally
* return ggml_tensor * pair in kda_autoregressive and kda_chunking as in ngxson's Qwen3Next improvement
* removed Kimi-Linear specific change that causes failure at server-windows
* removed private: from kimi_linear to make build checks happy
* removed unnecessary ggml_cont before ggml_reshape
* created static function causal_conv1d to abtract similar code for q/k/v
* merged dt_bias to SSM_DT. Do -exp(log_A) in convert_hf_to_gguf.py.
* reverted to original
* fixed find_hparam calls. Fixed e_score_correction_bias to use bias instead of weight. Removed all ssm_conv bias terms.
* remove DT_B from constants.py. remove one comment line in llama-model.cpp
* new class llm_graph_input_mem_hybrid_k to get around the new MLA change. switch the concat order of ggml_concat calls in kimi-linear.cpp to accommodate MLA changes. Removed support for exp_probs_b.weight
* remove ssm_o_norm_b
* remove ssm_o_norm_b
* changed hparams.kda_head_dim to hparams.n_embd_head_kda. added TODO comment for class llama_graph_mem_hybrid_k
* removed all ggml_cont b4 ggml_reshape_4d
* Whitespace
* replaced all hparams.get with find_hparams
* added new names for n_experts, n_experts_used and score_func in TextModel and removed their code in KimiLinear in convert_hf_to_gguf.py. Removed unnecessary ggml_cont and GGML_ASSERT in kimi-linear.cpp
* use is_mla to switch between different mem_hybrid types
* fixed logical errors in convert_hf_to_gguf.py pointed out by CISC
* removed if else for required parameters kv_lora_rank and qk_rope_head_dim
* add back ggml_cont for Vcur
* minor changes
* removed extra line in llama-vocab.cpp. Added back the comment in llama-graph.cpp
Jeff Bolz [Fri, 6 Feb 2026 08:15:13 +0000 (02:15 -0600)]
vulkan: For coopmat2 FA, use fp16 accumulators for the final result (#19376)
The cpu and cuda backends use fp16 for the VKQ accumulator type, this change
does the same for vulkan. This helps particularly with large head sizes which
are very register-limited.
I tried this for the coopmat1 path and it slowed down a bit. I didn't try for
scalar.
I applied the softmax bias that the cuda backend uses to avoid overflow,
although I was not able to reproduce the original bug without it.
This commit adds a new python script that can be used to print tensors
information from a tensor in a safetensors model.
The motivation for this is that during model conversion work it can
sometimes be useful to verify the shape of tensors in the original
model. While it is possible to print the tensors when loading the model
this can be slow when working with larger models.
With this script it is possible to quickly query tensor shapes.
positional arguments:
tensor_name Name of the tensor to inspect
options:
-h, --help show this help message and exit
-m MODEL_PATH, --model-path MODEL_PATH
Path to the model directory (default: MODEL_PATH environment variable)
-l, --list List unique tensor patterns in the model (layer numbers replaced with #)
```
This commit simplifies the processing of embd by removing the for loop
that currently exists which uses params.n_batch as its increment. This
commit also removes the clamping of n_eval as the size of embd is always
at most the size of params.n_batch.
The motivation is to clarify the code as it is currently a little
confusing when looking at this for loop in isolation and thinking that
it can process multiple batches.
* add an assert to verify n_eval is not greater than n_batch
Oliver Simons [Tue, 3 Feb 2026 10:33:14 +0000 (11:33 +0100)]
CUDA: Fix loop unrolling for BW in mul_mat_q_stream_k_fixup (#19053)
By providing stride_* variables as size_t (i.e., 64-bit) the compiler can
correctly unroll the [two for-loops](https://github.com/ggml-org/llama.cpp/blob/557515be1e93ed8939dd8a7c7d08765fdbe8be31/ggml/src/ggml-cuda/mmq.cuh#L3789-L3816)
on BW. This gives some perf for prefill/pp phase on BW, while not affecting
other SMs:
Gaurav Garg [Tue, 3 Feb 2026 06:41:02 +0000 (12:11 +0530)]
cuda : revert CUDA_SCALE_LAUNCH_QUEUES override until investigated (#19227)
Hangs were reported on Jetson Orin AGX if we set CUDA_SCALE_LAUNCH_QUEUES=4x. Reverting the previous PR (#19042) and updating the document to consider setting CUDA_SCALE_LAUNCH_QUEUES=4x for faster throughput on multi-GPU systems.
Sid Mohan [Mon, 2 Feb 2026 20:00:55 +0000 (12:00 -0800)]
jinja : add missing 'in' test to template engine (#19004) (#19239)
* jinja : add missing 'in' test to template engine (#19004)
The jinja template parser was missing the 'in' test from
global_builtins(), causing templates using reject("in", ...),
select("in", ...), or 'x is in(y)' to fail with
"selectattr: unknown test 'in'".
This broke tool-calling for Qwen3-Coder and any other model
whose chat template uses the 'in' test.
Added test_is_in supporting array, string, and object containment
checks, mirroring the existing 'in' operator logic in runtime.cpp.
Includes test cases for all three containment types plus
reject/select filter usage.
Co-Authored-By: Claude Opus 4.5 <redacted>
* reuse test_is_in in binary op
---------
Co-authored-by: Sid Mohan <redacted> Co-authored-by: Claude Opus 4.5 <redacted> Co-authored-by: Xuan Son Nguyen <redacted>
Matthieu Coudron [Mon, 2 Feb 2026 15:55:27 +0000 (16:55 +0100)]
server: print actual model name in 'model not found" error (#19117)
Experimenting with AI, my environment gets messy fast and it's not
always easy to know what model my software is trying to load. This helps
with troubleshooting.
before:
Error: {
code = 400,
message = "model not found",
type = "invalid_request_error"
}
After:
Error: {
code = 400,
message = "model 'toto' not found",
type = "invalid_request_error"
}
Neo Zhang [Mon, 2 Feb 2026 13:06:21 +0000 (21:06 +0800)]
Remove support for Nvidia & AMD GPU, because the oneAPI plugin for Nvidia & AMD GPU is unavailable: download/installation channels are out of work. (#19246)
User can't build up the software for Nvidia & AMD GPU.
rm the oneMath since it is only used in NV and AMD code path.
Daniel Bevenius [Mon, 2 Feb 2026 10:29:57 +0000 (11:29 +0100)]
model-conversion : add debug option to conversion script (#19265)
This commit adds a debug option to the model conversion script to enable
using the Python debugger (pdb) during model conversion.
The motivation for this is that I've found myself adding this a few
times now and it would be quicker to have this flag as an option and a
makefile target/recipe for it.
overview / pkg / ggml / sources / llama.cpp / log