Commit Graph

8036 Commits

Author SHA1 Message Date
Piotr Wilkin 61e18cad3f Create basic content parser if no parser definition found 2026-02-14 00:26:17 +01:00
Piotr Wilkin 3605e78569 Refactor into class-based approach 2026-02-14 00:17:43 +01:00
Piotr Wilkin 6415d0f03f Add TODO 2026-02-13 14:42:26 +01:00
Piotr Wilkin 24cc1bcd6d Clean algorithm for calculate_diff_split; fix buggy expectations 2026-02-13 03:17:20 +01:00
Piotr Wilkin e772822011 Whitespace 2026-02-13 00:55:56 +01:00
Piotr Wilkin 28fcef67c0 -> Refactor autoparser analyzer structure
-> Fix content truncation
-> Fix errors in capability detection due to non-empty assistant message
-> Add missing debug prints for Jinja
2026-02-13 00:55:35 +01:00
Piotr Wilkin 822fd2bee9 Whoops 2026-02-12 17:22:59 +01:00
Piotr Wilkin 3096ecaa95 One more crazy spacing out 2026-02-11 23:44:52 +01:00
Piotr Wilkin e40d4cd706 Get rid of some crazy formatting 2026-02-11 22:53:02 +01:00
Piotr Wilkin 56ca124850 Document helpers 2026-02-11 22:42:16 +01:00
Piotr Wilkin efc52dadc8 Add compilation guard to fix Windows compilation errors 2026-02-11 13:47:30 +01:00
Piotr Wilkin d69ec41ee0 Post-merge adapt 2026-02-11 13:47:30 +01:00
Piotr Wilkin e590f31f67 Revert obsolete server-context change 2026-02-11 13:47:30 +01:00
Piotr Wilkin 29ce31b1a3 Fix windows build 2026-02-11 13:47:30 +01:00
Piotr Wilkin 92acde0890 Regenerate documentation 2026-02-11 13:47:30 +01:00
Piotr Wilkin bd549b3b37 Fix case with object inside object, refactor long methods. 2026-02-11 13:47:29 +01:00
Piotr Wilkin 2081e9b056 Fix number partial parsing issue 2026-02-11 13:47:29 +01:00
Piotr Wilkin b260de1d86 More edge cases 2026-02-11 13:47:29 +01:00
Piotr Wilkin 60717b3e5a Fix pesky issue on optional trailing arguments in function calls for TAGGED format 2026-02-11 13:47:29 +01:00
Piotr Wilkin c2f6fc3a17 Remove [[noreturn]] as it causes compilation problems on Mac. 2026-02-11 13:47:29 +01:00
Piotr Wilkin 15f7aa1fbe We don't like segfaults (or failing tests). 2026-02-11 13:47:29 +01:00
Piotr Wilkin f71ae707ba Fix minor regressions, add [[noreturn]] attrib 2026-02-11 13:47:29 +01:00
Piotr Wilkin 09b447a487 Fix incorrect coercion of strings to non-string types during parsing 2026-02-11 13:47:29 +01:00
Piotr Wilkin a01e15280a Feeding the hungry editor checker god. 2026-02-11 13:47:29 +01:00
Piotr Wilkin 384cafc98b Fix error in argument processing 2026-02-11 13:47:29 +01:00
Piotr Wilkin 3770566c45 Reverd bad change fix some templates and most tests 2026-02-11 13:47:29 +01:00
Piotr Wilkin 9ba9a94819 More robust reasoning detection 2026-02-11 13:47:29 +01:00
Piotr Wilkin 80b7e161ff Fix reasoning detection 2026-02-11 13:47:29 +01:00
Piotr Wilkin b0853baca7 Quick vibe-coded fix for proper object printing 2026-02-11 13:47:29 +01:00
Piotr Wilkin c7029f858d Missed this. 2026-02-11 13:47:29 +01:00
Piotr Wilkin 1662fa5bea ANOTHER GIANT POST-FIXUP SQUISH 2026-02-11 13:47:29 +01:00
Piotr Wilkin 7e6f75a414 THE GIANT AUTOPARSER SQUISH 2026-02-11 13:47:29 +01:00
Piotr Wilkin 571805b348 Make call IDs nine-character 2026-02-11 13:47:29 +01:00
Piotr Wilkin 93f0cc05de Fix sanitizer warnings 2026-02-11 13:47:29 +01:00
Piotr Wilkin 96316496d5 Fix bad typo 2026-02-11 13:47:29 +01:00
Piotr Wilkin 9a3ac05157 Add workaround for templates requiring non-null content 2026-02-11 13:47:29 +01:00
Johannes Gäßler ada90bf2ba
docs: ban AI for issues and discussions [no CI] (#19512) 2026-02-11 12:49:40 +01:00
Adrien Gallouët 0c1f39a9ae
common : improve download error reporting (#19491)
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-02-11 09:27:55 +01:00
Max Krasnyansky 73cd5e1b97
hexagon: Add ARGSORT, DIV, SQR, SQRT, SUM_ROWS, GEGLU (#19406)
* hexagon: add ARGSORT op

Co-authored-by: Yarden Tal <yardent@qti.qualcomm.com>

* hexagon: argsort reject tensors with huge rows for now

* Adding support for DIV,SQR,SQRT,SUM_ROWS ops in hexagon backend

* hexagon : Add GEGLU op

* hexagon: fix editor config check

* hexagon: rewrite and optimize binary ops ADD/SUB/MUL/DIV/ADD_ID to use DMA

---------

Co-authored-by: Yarden Tal <yardent@qti.qualcomm.com>
Co-authored-by: Manohara Hosakoppa Krishnamurthy <mhosakop@qti.qualcomm.com>
2026-02-10 23:21:12 -08:00
thecaptain789 8ee538ce73
llama : correct typos 'occured' and 'occurences' (#19414)
Co-authored-by: thecaptain789 <thecaptain789@users.noreply.github.com>
2026-02-11 07:05:31 +01:00
Georgi Gerganov 6d95707827
model : fix wavtokenizer embedding notions (#19479) 2026-02-11 07:52:20 +02:00
Georgi Gerganov 89181c0b6d
ggml : extend bin bcast for permuted src1 (#19484)
* tests : extend bin bcast for permuted src1

* cont : extend bin support

* cont : s0 is always 1

* tests : simplify
2026-02-11 07:52:00 +02:00
Georgi Gerganov ceaa89b786
metal : consolidate unary ops (#19490) 2026-02-11 07:51:12 +02:00
Daniel Bevenius 2cce9fddb7
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.
2026-02-11 05:38:13 +01:00
Oliver Simons 612db61886
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.

https://github.com/NVIDIA/cccl/releases/tag/v3.2.0
2026-02-10 22:31:19 +01:00
Nikhil Jain 57487a64c8
[WebGPU] Plug memory leaks and free resources on shutdown (#19315)
* Fix memory leaks in shader lib, backend, backend_context, buffer_context, and webgpu_buf_pool

* Free pools

* Cleanup

* More cleanup

* Run clang-format

* Fix arg-parser and tokenizer test errors that free an unallocated buffer

* Fix device lost callback to not print on device teardown

* Fix include and run clang-format

* remove unused unused

* Update binary ops

---------

Co-authored-by: Reese Levine <reeselevine1@gmail.com>
2026-02-10 08:04:00 -08:00
JJJYmmm fc0fe40049
models : support qwen3.5 series (#19468)
* support qwen3.5 series

* remove deepstack for now, and some code clean

* code clean

* add FULL_ATTENTION_INTERVAL metadata

* code clean

* reorder v heads for linear attention to avoid expensive interleaved repeat
2026-02-10 18:00:26 +02:00
Xuan-Son Nguyen 9a96352729
test: fix IMROPE perf test case (#19465) 2026-02-10 14:37:50 +01:00
Alberto Cabrera Pérez c03a5a46f0
ggml-cpu: arm64: q6_K repack gemm and gemv (and generic) implementations (dotprod) (#19360)
* First working version of GEMM and GEMV

* interleave loads and compute

* Clang-format

* Added missing fallback. Removed tested TODO.

* Swap M and N to be consistent with the repack template convention
2026-02-10 10:47:45 +00:00
k4ss4n 6948adc90d
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)

Resolves: #18560
2026-02-10 10:57:48 +01:00