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
```
* `matched_graph` is obtained even if graph mode is disabled.
* End of graph capture and graph replay are unnecessarily placed in different `if` blocks.
**Proposed solution**
* Obtain `matched_graph` only if graph mode is enabled.
* Place end of graph capture and graph reply inside the same `if` block.
* Unify graph related comments.
Jeff Bolz [Wed, 19 Nov 2025 16:25:50 +0000 (10:25 -0600)]
vulkan: support larger argsort (#17313)
* vulkan: support larger argsort
This is an extension of the original bitonic sorting shader that puts the
temporary values in global memory and when more than 1024 threads are needed
it runs multiple workgroups and synchronizes through a pipelinebarrier.
To improve the memory access pattern, a copy of the float value is kept with
the index value. I've applied this same change to the original shared memory
version of the shader, which is still used when ncols <= 1024.
* Reduce the number of shader variants. Use smaller workgroups when doing a single pass, for a modest perf boost
* reduce loop overhead
* run multiple cols per invocation, to reduce barrier overhead
* Add proper handling of optional parameters with test
merged tests from: https://github.com/ggml-org/llama.cpp/pull/16946/commits/23d4bb75c485c12ac89f81c424dc03c87a640e8c
* Fix making all tool parameters optional
* Move xml tool parser to separate file
* cleanup & add tests for GLM4.5
* add streaming tests & enhancement & cleanups
Add streaming test for both GLM 4.5 and minimax-m2.
Cleanup for preserved_tokens.
Cleanup for grammar rule name.
Enhance the parser's stability.
* cleanup & add support for Kimi-K2 Qwen3-Coder Apriel-1.5 Xiaomi-MiMo
* apply suggestions from reviewers
* fix a misuse for data.grammar_lazy
* fix grammar when tool have no argument
* Fix `no triggers set for lazy grammar!` for GLM4.5/4.6. Insert additional stops for Kimi-K2
Co-authored-by: Sigbjørn Skjæret <redacted>
* improve chat template for GLM, rename Kimi-K2 template to Kimi-K2-Thinking
* Improve Kimi-K2 chat template
* Fix unit test
* Fix "Invalid tool call arguments passed" in a rare case.
In a rare case, the model may emit a raw string that begins with a valid JSON string. This commit adds unit tests to cover that scenario and fixes the regression introduced during the Kimi-K2 adaptation.
Chenguang Li [Tue, 18 Nov 2025 08:41:52 +0000 (16:41 +0800)]
CANN: fix acl_tensor_ptr usage in ASCEND_310P ROPE (#17347)
* cann: fix acl_tensor_ptr usage in ASCEND_310P ROPE implementation
Fix compilation errors in the ASCEND_310P-specific ROPE operation code
by adding .get() calls when passing acl_tensor_ptr smart pointers to
functions expecting raw aclTensor* pointers.
This fixes the code that was missed in the previous refactoring commit
(8981848) which changed ggml_cann_create_tensor() return type from
aclTensor* to acl_tensor_ptr.
hipudding [Mon, 17 Nov 2025 00:43:59 +0000 (08:43 +0800)]
CANN: Use smart pointers to manage ACL objects (#17238)
* CANN: Use smart pointers to manage ACL objects
Previously, ACL objects were managed via manual destruction, which
led to multiple memory-leak issues during runtime. This patch replaces
manual memory management with smart pointers so that ACL objects
are properly released and ownership is clearly defined.
Note that the ownership of an ACL object belongs to the function
that creates it. Other internal functions should operate on these ACL
objects using raw pointers to avoid unintended ownership transfers.
Additionally, since aclTensorList automatically frees its contained
aclTensor objects, any aclTensor added to a tensor list must release
ownership to avoid double free operations.
This PR also removes the asynchronous task submission mechanism.
Due to changes in recent CANN versions, tiling time has significantly
decreased. Even with a dual-thread submission model, the dispatch
overhead still falls on the critical path, making async submission
less beneficial. Moreover, aclGraph support provides a much better
path to reducing operator dispatch latency.
Pascal [Sat, 15 Nov 2025 20:09:32 +0000 (21:09 +0100)]
webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI (#16618)
* webui: add OAI-Compat Harmony tool-call live streaming visualization and persistence in chat UI
- Purely visual and diagnostic change, no effect on model context, prompt
construction, or inference behavior
- Captured assistant tool call payloads during streaming and non-streaming
completions, and persisted them in chat state and storage for downstream use
- Exposed parsed tool call labels beneath the assistant's model info line
with graceful fallback when parsing fails
- Added tool call badges beneath assistant responses that expose JSON tooltips
and copy their payloads when clicked, matching the existing model badge styling
- Added a user-facing setting to toggle tool call visibility to the Developer
settings section directly under the model selector option
Jeff Bolz [Sat, 15 Nov 2025 08:06:41 +0000 (02:06 -0600)]
vulkan: change graph_compute to be async and enable get_tensor_async (#17158)
* vulkan: change graph_compute to be async and enable get_tensor_async
This allows some additional CPU/GPU overlap for large pp workloads. Also seems
to help a bit for token gen, maybe getting rid of a small bubble between
graph_compute and get_tensor.
Async set and copy functions seem to be very rarely used, so I didn't enable
them because I didn't have a good way to test them.
The async commands need to be ordered against each other, so put them all on
the compute queue. The non-async commands still use the transfer queue.
The fence for graph_compute/get_tensor_async is submitted and waited on in
ggml_vk_synchronize.
overview / pkg / ggml / sources / llama.cpp / log