893dbb058a
fix: skip sending image attachments to non-vision backends
2026-02-01 03:20:36 +01:00
556029eee6
chore: update webui build output
2026-01-31 08:27:11 +01:00
1384352484
fix: responsive MCP server cards, prioritize server name over version
2026-01-31 08:22:41 +01:00
1615b1c58c
fix: responsive MCP server cards for mobile viewports
2026-01-31 07:58:47 +01:00
cd8e5741f2
chore: update webui build output
2026-01-30 20:23:45 +01:00
b872838329
webui: adaptive model selector dropdown width
...
Make model selector dropdown responsive:
- Mobile: full width (w-full max-w-[100vw])
- Desktop: adapts to longest model name (sm:w-max)
- Replace TruncatedText with responsive span (truncate on mobile, full text on desktop via sm:overflow-visible sm:whitespace-nowrap)
- Center status icons in fixed 24px wrapper to prevent layout shifts
- Add sm:pr-2 padding between text and icon zone on desktop
Fixes dropdown cutting off long model names on desktop while maintaining full-width display on mobile with proper text truncation
2026-01-30 20:21:05 +01:00
120ada3616
chore: update webui build output
2026-01-29 16:31:07 +01:00
e41f70bb47
refactor: Use CORS Proxy for favicons calls
2026-01-29 16:30:10 +01:00
46c5bca942
refactor: Proxy utility
2026-01-29 16:29:04 +01:00
944765138e
chore: update webui build output
2026-01-29 15:03:00 +01:00
536c6866e3
feat: Integrate with `llama-server` proxy + improve MCP Server Edit Form
2026-01-29 14:59:28 +01:00
406cb1dd99
Merge remote-tracking branch 'ngxson/xsn/cors_proxy_demo' into allozaur/mcp-mvp
2026-01-29 13:34:20 +01:00
9d6e210a5e
Merge remote-tracking branch 'ggml-org/master' into allozaur/mcp-mvp
2026-01-29 13:21:44 +01:00
7b00b46a6a
chore: update webui build output
2026-01-29 12:55:45 +01:00
6793c7daac
fix: Checking for capabilities from store
2026-01-29 12:45:10 +01:00
2aa704b821
refactor: Cleanup
2026-01-29 11:44:08 +01:00
f3dd7b8e68
HIP: add mmf for CDNA ( #18896 )
...
* refactor mmf rows_per_block
* speed up compile
* pass cdna compile
* fix cuda error
* clean up mmf
* f32 mmf
* clean float mma
* fix mmf error
* faster mmf
* extend tile k
* fix compile error
* Revert "extend tile k"
This reverts commit 4d2ef3d483
2026-01-29 11:10:53 +01:00
eed25bc6b0
arg : add -kvu to llama-batched-bench ( #19172 )
2026-01-29 08:50:47 +02:00
b33df266d0
ggml-zendnn : resolve ZenDNN backend cross-module symbol dependency ( #19159 )
2026-01-29 12:28:57 +08:00
3bcc990997
CUDA: refactor topk-moe to enable more models (GLM 4.7, Nemotron etc.) ( #19126 )
2026-01-29 10:31:28 +08:00
d4964a7c66
sycl: fix norm kernels: l2_norm, group_norm, rms_norm by remove assert to support more cases ( #19154 )
...
Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>
2026-01-29 09:20:22 +08:00
50e8962f79
ci : find latest release with asset for winget ( #19161 )
2026-01-28 22:05:39 +01:00
c7b7fc6c15
chore: update webui build output
2026-01-28 19:57:18 +01:00
d9e82b7c29
fix: Linter errors
2026-01-28 19:55:44 +01:00
f6b533d898
Vulkan Flash Attention Coopmat1 Refactor ( #19075 )
...
* vulkan: use coopmat for flash attention p*v matrix multiplication
* fix P loading issue
* fix barrier position
* remove reduction that is no longer needed
* move max thread reduction into loop
* remove osh padding
* add bounds checks and padding
* remove unused code
* fix shmem sizes, loop duration and accesses
* don't overwrite Qf, add new shared psh buffer instead
* add missing bounds checks
* use subgroup reductions
* optimize
* move bounds check, reduce barriers
* support other Bc values and other subgroup sizes
* remove D_split
* replace Of register array with shared memory Ofsh array
* parallelize HSV across the rowgroups
* go back to Of in registers, not shmem
* vectorize sfsh
* don't store entire K tile in shmem
* fixes
* load large k tiles to shmem on Nvidia
* adapt shared memory host check function to shader changes
* remove Bc 32 case
* remove unused variable
* fix missing mask reduction tmspsh barrier
* fix mask bounds check
* fix rowmax f16 under/overflow to inf
* fix flash_attn_cm2 BLOCK_SIZE preprocessor directives
2026-01-28 18:52:45 +01:00
72d3b1898a
spec : add self‑speculative decoding (no draft model required) + refactor ( #18471 )
...
* server: introduce self-speculative decoding
* server: moved self-call into speculative.cpp
* can_speculate() includes self-speculation
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* server: can_speculate() tests self-spec
* server: replace can_speculate() with slot.can_speculate()
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* common: use %zu format specifier for size_t in logging
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* server: can_speculate() requires a task instance
* common: ngram map, config self-speculative decoding
* common: add enum common_speculative_type
* common: add vector of speculative states
* common: add option --spec-draftless
* server: cleanup (remove slot.batch_spec, rename)
* common: moved self-spec impl to ngram-map
* common: cleanup (use common_speculative_state_draft)
* spec : refactor
* cont : naming
* spec: remove --spec-config
* doc: (draftless) speculative decoding
* common: print performance in spec decoding
* minor : cleanup
* common : better names
* minor : cleanup + fix build
* minor: comments
* CODEOWNERS: add common/ngram-map.* (#18471 )
* common : rename speculative.draftless_type -> speculative.type
* ngram-map : fix uninitialized values
* ngram-map : take into account the input can become shorter
* ngram-map : revert len check for now
* arg : change `--spec-draftless` -> `--spec-type`
* spec : add common_speculative_state::accept()
* spec : refactor + add common_speculative_begin()
* spec : fix begin() call with mtmd
* spec : additional refactor + remove common_speculative_params
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-01-28 19:42:42 +02:00
7c9be63a74
refactor: Refine Chat Message Processing State Display
2026-01-28 18:31:37 +01:00
5a176d1893
feat: Chat logic improvements
2026-01-28 18:31:37 +01:00
aa7089d598
feat: Integrate Resource Attachments into Chat Form UI
2026-01-28 18:31:37 +01:00
23e4ef7495
feat: MCP Resources UI
...
feat: Implement MCP Resource Selection Dialog
2026-01-28 18:31:37 +01:00
1623547e2b
feat: Integrate Resource Store into Main MCP Store
2026-01-28 18:31:36 +01:00
dc2076a77c
feat: MCP Resources Svelte Store
2026-01-28 18:31:36 +01:00
192c920d73
refactor: Use constants
2026-01-28 18:31:35 +01:00
89166a79d4
feat: Introduce MCP Resource Types and Service Methods
2026-01-28 18:31:35 +01:00
85a61a7c96
refactor: Componentize HorizontalScrollCarousel
2026-01-28 17:32:59 +01:00
bfbcdc7420
fix: Code Preview sandbox
2026-01-28 17:31:04 +01:00
ebf5725870
convert : yield Mamba2Model/GraniteMoeModel modify_tensors ( #19157 )
...
* convert : yield Mamba2Model/GraniteMoeModel modify_tensors
This commit updates the `GraniteHybridModel` class' modify_tensors
function to properly delegate to `Mamba2Model.modify_tensors` and
`GraniteMoeModel.modify_tensors` using 'yield from' instead of 'return'.
The motivation for this is that modify_tensors is a generator function
(it uses 'yield from'), but the two calls above use return statements
but don't yield anything which means that the the caller of this
function will not receive any yielded values from it. And this causes
layer tensors to be silently dropped during conversion.
2026-01-28 16:49:36 +01:00
0cd7032ca4
ggml-sycl: remove unused syclcompat header ( #19140 )
...
The syclcompat/math.hpp is not used anymore. The change that intrduced it was successfuly reverted (https://github.com/ggml-org/llama.cpp/pull/17826 ).
This include path will become obsolete and dropped in oneAPI 2026.0 effectively breaking ggml-sycl builds.
2026-01-28 23:33:54 +08:00
60368e1d73
jinja : undefined should be treated as sequence/iterable (return string/array) by filters/tests ( #19147 )
...
* undefined is treated as iterable (string/array) by filters
`tojson` is not a supported `undefined` filter
* add tests
* add sequence and iterable tests
keep it DRY and fix some types
2026-01-28 14:40:29 +01:00
88d23ad515
vulkan: handle device dedup on MacOS + Vega II Duo cards ( #19058 )
...
Deduplication here relied on the fact that vulkan would return unique
UUID for different physical GPUs. It is at the moment not always the case.
On Mac Pro 2019 running Mac OS, with 2 Vega II Duo cards (so, 4 GPU total),
MotlenVK would assign same UUID to pairs of GPUs, unless they
are connected with Infinity Fabric.
See more details here: KhronosGroup/MoltenVK#2683 .
The right way is to fix that in MoltenVK, but until it is fixed,
llama.cpp would only recognize 2 of 4 GPUs in such configuration.
The deduplication logic here is changed to only filter GPUs if UUID is
same but driver is different.
2026-01-28 12:35:54 +01:00
0a95026da9
doc: add build instruction to use Vulkan backend on macos ( #19029 )
2026-01-28 12:30:16 +01:00
b7feacf7f3
ggml: new backend for Virglrenderer API Remoting acceleration (v2) ( #18718 )
2026-01-28 17:49:40 +08:00
6ad70c5a77
ggml-cpu: arm64: Q4_K scale unroll and vectorization ( #19108 )
2026-01-28 09:15:56 +02:00
631cbfcc7a
cuda : fix "V is K view" check for non-unified KV cache ( #19145 )
2026-01-28 09:15:27 +02:00
2eee6c866c
CUDA: tune GLM 4.7 Flash FA kernel selection logic (DGX Spark) ( #19142 )
2026-01-28 09:15:11 +02:00
b931f81b5a
server : adjust spec tests to generate up to 16 tokens ( #19093 )
2026-01-28 09:11:40 +02:00
c5c64f72ac
llama : disable Direct IO by default ( #19109 )
...
* llama : disable Direct IO by default
* cont : override mmap if supported
2026-01-28 09:11:13 +02:00
eef375ce16
sampling : remove sampling branching in output_reserve ( #18811 )
...
* sampling : remove sampling branching in output_reserve
This commit updates output_reserve in llama-context.cpp to always
allocate sampling buffers regardless of whether sampling is needed for
the current batch.
The motivation for this is to avoid reallocations and branching based on
the sampling requirements of the batch.
2026-01-28 05:59:30 +01:00
06961e2876
ggml webgpu: Split shared state (webgpu_context) into global state and per-thread state ( #18976 )
...
* Squashed commit of the following:
commit b3c6bf4b0450d8d452b934df27a0fb7cb53cd755
Author: Abhijit Ramesh <abhijitramesh2k@gmail.com>
Date: Mon Dec 1 18:29:00 2025 -0800
ggml webgpu: fix xielu parameter passing (#11 )
The XIELU operation was incorrectly using static_cast to convert
float parameters to uint32_t, which converted numeric values instead
of preserving IEEE 754 bit patterns. This caused incorrect values
to be interpreted by the GPU shader.
* Use reinterpret_cast to preserve float bit patterns when passing
through uint32_t params buffer
* Update WGSL shader parameter types from u32 to f32
* Re-enable XIELU support (was disabled due to numerical issues)
Fixes NMSE test failures for XIELU operation on WebGPU backend.
commit 5ca9b5e49e#10 )
* refactored pipelines
* refactored workgroup calculation
* removed commented out block of prior maps
* Clean up ceiling division pattern
---------
Co-authored-by: Neha Abbas <nehaabbas@eduroam-169-233-141-223.ucsc.edu>
Co-authored-by: Reese Levine <reeselevine1@gmail.com>
Author: James Contini <jamescontini@gmail.com>
Date: Wed Oct 29 23:13:06 2025 -0700
formatted embed wgsl and ggml-webgpu.cpp
commit e1f6baea318c70b8fecef9282c660c4cf28d7dec74c6add176362749910bcb085833375360e2852a7b09baa4aa8a6ec84374b8fc178a6ec843a5c3ae38278aaa1c9b2f88
2026-01-27 20:53:36 -08:00
f2571df8b7
ggml-zendnn : update ZenDNN git tag to main branch ( #19133 )
2026-01-28 06:21:36 +08:00
Pascal
Aleksander Grygier
yulo
Georgi Gerganov
Vishal Singh
Aman Gupta
Neo Zhang
Sigbjørn Skjæret
Ruben Ortlam
Sascha Rogmann
Daniel Bevenius
Patryk Kaminski
Oleksandr Kuvshynov
Ben Chen
Kevin Pouget
Alberto Cabrera Pérez
Nikhil Jain