Jeff Bolz [Tue, 2 Dec 2025 18:22:04 +0000 (12:22 -0600)]
vulkan: Reduce temporary memory usage for TOP_K (#17623)
- Compute row size for the temp buffer based on the output of the first pass.
- Update shader addressing math to use the output row size
- Pass the output row size as "ncols_output", what used to be "ncols_output" is now "k"
For the common case of K=40 and src0=(200000,1,1,1), this reduces the temporary buffer
from about 3.2MB to 500KB.
Eric Curtin [Tue, 2 Dec 2025 11:18:15 +0000 (11:18 +0000)]
codeowners : remove ericcurtin (#17658)
Taking a break from llama.cpp . I wasn't around at the start of llama.cpp
but I want to thank @ggerganov and @slaren for creating a neat community
here.
Refactors components to access stores directly instead of using exported getter functions.
This change centralizes store access and logic, simplifying component code and improving maintainability by reducing the number of exported functions and promoting direct store interaction.
Removes exported getter functions from `chat.svelte.ts`, `conversations.svelte.ts`, `models.svelte.ts` and `settings.svelte.ts`.
* refactor: Architecture cleanup
* feat: Improve statistic badges
* feat: Condition available models based on modality + better model loading strategy & UX
* docs: Architecture documentation
* feat: Update logic for PDF as Image
* add TODO for http client
* refactor: Enhance model info and attachment handling
* chore: update webui build output
* refactor: Components naming
* chore: update webui build output
* refactor: Cleanup
* refactor: DRY `getAttachmentDisplayItems` function + fix UI
* chore: update webui build output
* fix: Modality detection improvement for text-based PDF attachments
* refactor: Cleanup
* docs: Add info comment
* refactor: Cleanup
* re
* refactor: Cleanup
* refactor: Cleanup
* feat: Attachment logic & UI improvements
* refactor: Constants
* feat: Improve UI sidebar background color
* chore: update webui build output
* refactor: Utils imports + move types to `app.d.ts`
gguf_new_metadata.py reads data from reader.
Reader doesn't byteswap tensors to native endianness.
But writer does expect tensors in native endianness to convert them
into requested endianness.
There are two ways to fix this: update reader and do conversion to native endianness and back,
or skip converting endianness in writer in this particular USE-case.
gguf_editor_gui.py doesn't allow editing or viewing tensor data.
Let's go with skipping excessive byteswapping.
If eventually capability to view or edit tensor data is added,
tensor data should be instead byteswapped when reading it.
Fredrik Hultin [Fri, 28 Nov 2025 11:57:04 +0000 (12:57 +0100)]
server : add Anthropic Messages API support (#17570)
* server : add Anthropic Messages API support
* remove -@pytest.mark.slow from tool calling/jinja tests
* server : remove unused code and slow/skip on test_anthropic_vision_base64_with_multimodal_model in test_anthropic_api.py
* server : removed redundant n field logic in anthropic_params_from_json
* server : use single error object instead of error_array in streaming response handler for /v1/chat/completions and use unordered_set instead of set in to_json_anthropic_stream()
* server : refactor Anthropic API to use OAI conversion
Radoslav Gerganov [Fri, 28 Nov 2025 08:33:51 +0000 (10:33 +0200)]
rpc : cache and reuse compute graphs (#15405)
Store the last computed graph and reuse it when possible.
Also do not return response from GRAPH_COMPUTE and assume it always
completes successfully. If this this is not the case, the server closes
the connection. This saves us a network round trip to the server.
Jeff Bolz [Wed, 26 Nov 2025 15:45:43 +0000 (09:45 -0600)]
vulkan: Implement top-k (#17418)
* 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.
Adrien Gallouët [Wed, 26 Nov 2025 13:14:41 +0000 (14:14 +0100)]
ggml : fix ARM feature verification (#17519)
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...
hipudding [Wed, 26 Nov 2025 08:44:19 +0000 (16:44 +0800)]
CANN: Add MROPE and IMROPE support (#17401)
* 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.
Aleksei Nikiforov [Tue, 25 Nov 2025 13:18:16 +0000 (14:18 +0100)]
convert : fix big-endian conversion (#17431)
* 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
Pascal [Tue, 25 Nov 2025 07:01:02 +0000 (08:01 +0100)]
webui: add rehype plugin to restore HTML in Markdown table cells (#17477)
* 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.
Daniel Bevenius [Mon, 24 Nov 2025 20:06:17 +0000 (21:06 +0100)]
llama : skip output reordering for single token batches (#17466)
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.
Daniel Bevenius [Mon, 24 Nov 2025 13:38:45 +0000 (14:38 +0100)]
examples : add -kvu to batched usage example [no ci] (#17469)
This commit adds the --kv-unified flag to the usage example
in the README.md file for the batched example.
The motivation for this is that without this flag the example will fail
with the following error:
```console
Hello my name is
split_equal: sequential split is not supported when there are coupled
sequences in the input batch (you may need to use the -kvu flag)
decode: failed to find a memory slot for batch of size 4
main: llama_decode() failed
```
Daniel Bevenius [Mon, 24 Nov 2025 11:51:50 +0000 (12:51 +0100)]
ggml : remove dirty flag from version string (ggml/1391)
This commit removes the "-dirty" suffix from the GGML version string.
The motivation for this change is to ensure that the version string
works with different ways of checking out ggml and using it in projects.
By removing the dirty flag from the version string, we avoid potential
artifacts like shared libraries getting a -dirty suffix in their names.
Instead, if the project is built from a dirty git state, the dirty flag
will be appended to the commit hash in the GGML_BUILD_COMMIT variable.
This will enable users to still identify that the build was made from
from a modified/dirty state even though the version might match a "real"
version.
For example, the commit can be produces as follows:
```c++
printf("commit: %s\n", ggml_commit());
```
Which would print the following for a dirty build:
```console
commit: 781baf2a-dirty
```
overview / pkg / ggml / sources / llama.cpp / log