As we only support static graphs for the time and we don't know the size
of the output of top-p, we have to do value-scaling same as for min-p
operator.
Further improvements can be applied to the unit-test (i.e. check for
equivalence of top_p happening on backend with top_p happening on cpu)
and also by constructing candidates and sorting those as opposed to
reversing the sort of the logits (this would be arange +
get_rows instead of argsort + get_rows)
Fix llama-save-load-state which currently fails by handling the case
when batch.logits is nullptr (like when loading state) by allocating
space for all outputs as CPU logits.
This commit updates the backend sampling implementation to support
intermixed usage of backend and CPU samplers within the same batch.
The initial implementation was developed as an all-or-nothing solution:
either perform backend sampling for the entire batch, or perform CPU
sampling for the entire batch.
The motivation for this change is to support batches with mixed
sequences. For example, we may have a backend sampler configured for
sequence 0, while sequence 1 in the same batch uses CPU sampling. This
was not supported in the initial implementation.
This issue manifested in llama-server with the webui: decoding with
backend samplers would work initially, but after changing to CPU
sampling, a slot (sequence) could still be using a backend sampler.
This meant that logits in output_reserve would not be allocated,
resulting in an error.
The solution in this commit inspects the batch to determine which
sampling modes are needed and allocates buffers accordingly. However,
there is a known inefficiency: when we have intermixed backend/CPU
samplers in the same batch, we currently copy all logits to the host,
even for sequences using backend samplers.
Added test_backend_cpu_mixed_batch to verify correct behavior with
mixed backend/CPU samplers in a single batch, including dynamic
sampler switching between decode calls.
Some changes were made in 5ea3be265b
which were incomplete. In the case of non-CUB, bitonic sort and its
limitations of ncols < 1024 have to apply, similar to argsort.cu
This commit removes the backend sampling chain from the common_sampler
structure and related functions.
The motivation for this change is that the backend samplers are not
currently set on the context, and if they are they would cause the
a graph reallocation to occur. Instead, the intialization is handled
like it currently is by llama_context's constructor.
This commit adds a macro guard around argsort_f32_i32_cuda_cub usage
in the top-k fallback path, falling back to bitonic sort when
GGML_CUDA_USE_CUB is not defined.
The motivation for this is that some environments like AMD HIP
do not have CUB available, causing compilation failure.
Refs: https://github.com/ggml-org/llama.cpp/actions/runs/19728226426/job/56523606840#step:6:208
This commit modifies the temperature sampling check to allow a
temperature value of zero. Previously, the check only allowed
positive temperature values, which excluded the valid case of
zero temperature.
The motivation for this is to enable a zero temperature setting which is
also currently causing the following test to fail:
```console
(venv) $ cd tools/server/tests
(venv) $ ./tests.sh unit/test_basic.py::test_load_split_model
```
* vulkan: Implement top-k
Each pass launches workgroups that each sort 2^N elements (where N is usually 7-10)
and discards all but the top K. Repeat until only K are left. And there's a fast
path when K==1 to just find the max value rather than sorting.
* fix pipeline selection
* vulkan: Add N-ary search algorithm for topk
* microoptimizations
This commit adds a function to check if a sampler is actually enabled,
meaning that it does not have values that disables its effect. This is
then used by the backend samplers initialization to avoid considering
samplers that are not enabled when determining the split point between
them.
The motivation for this is that this allows the default sampler chain
for `--samplers` to be used and any sampler that is not enabled will not
cause the backend samplers to be skipped.
For example, before this change if the penalties sampler was included in
the samplers list but had default values that disable it, it would cause
the backend samplers to be skipped entirely.
This commit also contains some refactoring to remove some code
duplication.
We have to separate the code path starting 3.28 because
`FetchContent_Populate` is now deprecated and will be completely removed
in a future version.
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
On arm64 with `cmake` version 3.31.6, the final feature verification fails:
-- ARM detected flags: -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+nossbs
-- Performing Test GGML_MACHINE_SUPPORTS_dotprod
-- Performing Test GGML_MACHINE_SUPPORTS_dotprod - Success
-- Performing Test GGML_MACHINE_SUPPORTS_i8mm
-- Performing Test GGML_MACHINE_SUPPORTS_i8mm - Success
-- Performing Test GGML_MACHINE_SUPPORTS_sve
-- Performing Test GGML_MACHINE_SUPPORTS_sve - Success
-- Performing Test GGML_MACHINE_SUPPORTS_sme
-- Performing Test GGML_MACHINE_SUPPORTS_sme - Failed
-- Performing Test GGML_MACHINE_SUPPORTS_nosme
-- Performing Test GGML_MACHINE_SUPPORTS_nosme - Success
-- Checking for ARM features using flags:
-- -U__ARM_FEATURE_SME
-- -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+nossbs+dotprod+i8mm+sve+nosme
-- Performing Test HAVE_DOTPROD
-- Performing Test HAVE_DOTPROD - Failed
-- Performing Test HAVE_SVE
-- Performing Test HAVE_SVE - Failed
-- Performing Test HAVE_MATMUL_INT8
-- Performing Test HAVE_MATMUL_INT8 - Failed
-- Performing Test HAVE_FMA
-- Performing Test HAVE_FMA - Success
-- Performing Test HAVE_FP16_VECTOR_ARITHMETIC
-- Performing Test HAVE_FP16_VECTOR_ARITHMETIC - Failed
-- Performing Test HAVE_SME
-- Performing Test HAVE_SME - Failed
-- Adding CPU backend variant ggml-cpu: -U__ARM_FEATURE_SME;-mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+nossbs+dotprod+i8mm+sve+nosme
We need to explicitly replace `;` with spaces from the list to make
`CMAKE_REQUIRED_FLAGS` work correctly...
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
* patch failed test case MUL_MAT(type_a=q4_0,type_b=f32,m=576,n=512,k=576,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1) for enabling WMMA on RDNA4
* Quick clean up on mma.cuh to add ggml_cuda_memcpy_1 back in for half2 and bfloat162
* CANN: ROPE supports both MROPE and IMROPE.
1. Optimize the caching logic of rope_cache_init.
2. Add support for mRoPE and i-mRoPE.
Note that on Ascend 910B devices, it is necessary to disable FA
in CLIP and disable NZ-format conversion. These two issues are
still under investigation.
* Resolve review comments
* Fix convert_hf_to_gguf.py script on s390x
Assume converted model data is originally little-endian.
Byteswap data on s390x after reading it to put values in correct presentation
for any transformation needed, like calculating weight tensors.
Then byteswap data to little-endian before passing it to GGUFWriter while
GGUFWriter will byteswap data back to big endian if big endian output is requested.
byteswap(inplace=True) calls don't work with lazy tensor and array wrappers.
Use byteswap with copying data to workaround this behaviour.
* Make GGUFWriter accept tensors in native endianness instead of little-endian
With this change if no byteswapping is actually needed, 2 excessive byteswaps can be omitted on s390x
* Fix byteswapping in convert_hf_to_gguf.py for remote models
This commit removes the `--backend-dist` option and instead uses the
configured --samplers chain to determine which samplers run on the
backend.
Backend sampling is still enabled using With `--backend_sampling`, and
the sampler chain, either explictly specified using `--samplers` or the
default, is automatically analyzed to determine which samplers can run
on the backend. The system finds the longest contiguous chain of
backend supported samplers from the start of the sampler sequence.
For example:
* If the chain is `top-k -> temperature -> top-p`, and both `top-k` and
`temperature` are backend-supported but `top-p` is not, then `top-k`
and `temperature` will run on the backend, while `top-p` and
subsequent samplers run on the CPU.
* If all configured samplers are supported, the final distribution
sampling will also happen on the backend, transferring only the
sampled token IDs back to the host.
* If the sampler chain starts with an unsupported sampler (e.g.,
`penalties`), all sampling runs on the CPU. Note that this is
currently the case with the default sampler so to use backend sampling
it is required to specify a sampler chain. See below for an example.
The following shows how llama-cli can be run with backend sampling:
```console
$ llama-cli -m models/Qwen2.5-VL-3B-Instruct-Q8_0.gguf \
--prompt 'What is the capital of Sweden?' \
-n 20 \
-no-cnv \
--verbose-prompt \
-ngl 40 \
--backend-sampling \
--samplers 'top_k;temperature'
```
In this case the all sampling will happen on the backend since both
`top_k` and `temperature` are supported backend samplers.
To enable a partial backend sampling (hybrid sampling), for example
running `top_k` and `temperature` on the backend and `typ_p` on the CPU
the following sampler chain could be specified:
```console
$ llama-cli -m models/Qwen2.5-VL-3B-Instruct-Q8_0.gguf \
--prompt 'What is the capital of Sweden?' \
-n 20 \
-no-cnv \
--verbose-prompt \
-ngl 40 \
--backend-sampling \
--samplers 'top_k;temperature;top_p'
```
If this looks good then I'll follow up with updates the llama-cli and
llama-server documentation to reflect these changes.
* webui: add rehype plugin to restore HTML in Markdown table cells
The remark/rehype pipeline neutralizes inline HTML as literal text
(remarkLiteralHtml) so that XML/HTML snippets in LLM responses display
as-is instead of being rendered. This causes <br> and <ul> markup in
table cells to show as plain text.
This plugin traverses the HAST post-conversion, parses whitelisted HTML
patterns (<br>, <ul><li>) from text nodes, and replaces them with actual
HAST element nodes. For lists, adjacent siblings must be combined first
as the AST fragmentation breaks pattern matching.
Strict validation rejects malformed markup, keeping it as raw text.
* chore: update webui build output
This commit adds a check to skip the output reordering logic when
n_outputs == 1. With a single output token, the data is trivially
sorted and the reordering code is currently doing unnecessary work
(resetting and rebuilding output_ids to the same values).
The motivation for this change is improved code clarity and avoiding
confusion when debugging. While the performance impact is probably
negligible, this unnecessary work happens on every decode call in
llama-server when processing batches with single-token outputs.
* first commit naive test to enable mmq for RDNA4
* adding appropriate WMMA instructions
* git rebase on top of master: fixing the correctness of the mat mul operations, updating layout mappings for RDNA4
* clean up merge conflicts
* add comments and code clean up
* PR clean up, addressed comments
* enable MMQ fallback on RDNA4
* addressed comments: add guards in load generic, separate wmma branch for use_mmq function
* Revert build-xcframework.sh
* Formating: remove trailing whitespace
* revert CMake files
* clean up after rebase: remove duplicated change, revert cmake files
* clean up after rebase: revert changes from build-xcframework.sh
* clean up: remove extra space line in mma.cuh
* Revert "clean up: remove extra space line in mma.cuh"
This reverts commit b39ed57c45.
Georgi Gerganov
Daniel Bevenius
Oliver Simons
Jeff Bolz
xctan
Adrien Gallouët
Jiacheng (Jason) Chen
hipudding
o7si
Aleksei Nikiforov
Diego Devesa
TianHao324
Pascal
Aaron Teo
Sigbjørn Skjæret