b6277

CUDA: Accelerate MXFP4 table lookup using `__byte_perm` (#15451)

* CUDA: optimize get_int_from_table_16

* CUDA: use v_perm_b32 to replace byte_perm on AMD GPUs

* revise documentation

---------

Co-authored-by: xix <[email protected]>
Co-authored-by: Johannes Gäßler <[email protected]>

b6096

llama : add gpt-oss (#15091)

* oai moe

* compat with new checkpoint

* add attn sink impl

* add rope scaling yarn

* logits match with latest transformers code

* wip chat template

* rm trailing space

* use ggml_scale_bias

* rm redundant is_swa_all

* convert interleaved gate_up

* graph : fix activation function to match reference (#7)

* vocab : handle o200k_harmony special tokens

* ggml : add attention sinks support (#1)

* llama : add attn sinks

* ggml : add attn sinks

* cuda : add attn sinks

* vulkan : add support for sinks in softmax

remove unnecessary return

* ggml : add fused swiglu_oai op (#11)

* ggml : add fused swiglu_oai op

* Update ggml/src/ggml-cpu/ops.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

* update CUDA impl

* cont : metal impl

* add vulkan impl

* test-backend-ops : more test cases, clean up

* llama : remove unfused impl

* remove extra lines

---------

Co-authored-by: Georgi Gerganov <[email protected]>

---------

Co-authored-by: slaren <[email protected]>

* repack mxfp4 upon conversion

* clean up a bit

* enable thinking

* add quick hack to render only some special tokens

* fix bf16 conversion

* remove vocab hack

* webui ok

* support chat parsing for gpt-oss

* fix webui

* direct mapping mxfp4, FINALLY

* force using mxfp4

* properly use lazy tensor

* ggml : add mxfp4

ggml : use e8m0 conversion instead of powf

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

change kvalues_mxfp4 table to match e2m1 (#6)

metal : remove quantization for now (not used)

cuda : fix disabled CUDA graphs due to ffn moe bias

vulkan : add support for mxfp4

cont : add cm2 dequant

* ggml : add ggml_add_id (#13)

* ggml : add ggml_add_id

* add cuda impl

* llama : add weight support check for add_id

* perf opt

* add vulkan impl

* rename cuda files

* add metal impl

* allow in-place ggml_add_id

* llama : keep biases on CPU with --cpu-moe

* llama : fix compile error

ggml-ci

* cuda : add fallback for __nv_cvt_e8m0_to_bf16raw

ggml-ci

* cleanup

ggml-ci

* sycl : fix supports_op for MXFP4

ggml-ci

* fix Unknown reasoning format

* ggml-cpu : fix AVX build

ggml-ci

* fix hip build

ggml-ci

* cuda : add mxfp4 dequantization support for cuBLAS

ggml-ci

* ggml-cpu : fix mxfp4 fallback definitions for some architectures

ggml-ci

* cuda : fix version required for __nv_cvt_e8m0_to_bf16raw

---------

Co-authored-by: Xuan Son Nguyen <[email protected]>
Co-authored-by: slaren <[email protected]>

b6006

quantize : update README.md (#14905)

* Update README.md

* Fix trailing whitespace

* Update README.md

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

---------

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

b5926

Merge branch 'ggml-org:master' into master

b5924

Merge branch 'ggml-org:master' into master

b5922

Merge branch 'ggml-org:master' into master

b5919

Merge branch 'ggml-org:master' into master

b5917

Merge branch 'ggml-org:master' into master

b5913

Update unicode.cpp

b5912

Merge branch 'master' of https://github.com/unslothai/llama.cpp