happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
8,448 Commits 551 Branches 5,758 Tags 1.4 GiB
Commit Graph

8448 Commits

Author SHA1 Message Date
Imad Saddik 70c10f0cc1
Merge f62e0d9b4e into 88915cb55c 2026-03-15 19:25:21 +00:00
Imad Saddik f62e0d9b4e chore: update webui build output 2026-03-15 19:25:09 +00:00
Imad Saddik 9e5d40a550 chore: set autoChatWidth to true by default 2026-03-15 19:18:21 +00:00
Georgi Gerganov 88915cb55c
server : fix wait in test_cancel_requests() test (#20601) 
* server : fix wait in test_cancel_requests() test

* codeowners : add team for server tests
 2026-03-15 20:54:37 +02:00
Sigbjørn Skjæret ebbf544ed1
sycl : fix for untransposed GDA recurrent state (#20583) 2026-03-15 19:10:15 +01:00
Imad Saddik 0dd4d9d588 chore: update webui build output 2026-03-15 18:09:22 +00:00
Imad Saddik d549ab4893 style: remove max width 48rem from agentic-content 2026-03-15 18:07:01 +00:00
Sigbjørn Skjæret b91d7dfe5b
ci : only save openvino caches on github-hosted master (#20593) 
* only save openvino ccache on master

* disable toolkit cache if self-hosted

* only cache on github-hosted runners

* remove toolkit cache [no ci]
 2026-03-15 18:58:13 +01:00
Imad Saddik a0eccc8652 chore: update webui build output 2026-03-15 17:55:17 +00:00
Imad Saddik 333bfc7231 chore: undo changes in ChatScreenProcessingInfo 2026-03-15 17:53:31 +00:00
Imad Saddik c6c63786c2 chore: update webui build output 2026-03-15 17:49:34 +00:00
Imad Saddik de04a9b0e6 style: reset the width of the processing info div 2026-03-15 17:48:16 +00:00
Imad Saddik 715ba4ee85 chore: update webui build output 2026-03-15 17:40:36 +00:00
Imad Saddik fa7d3a96c5 fix: keep the container spanning the whole width to fix scroll bar issue 2026-03-15 17:39:19 +00:00
Imad Saddik c399ec3c46 chore: update webui build output 2026-03-15 17:36:11 +00:00
Imad Saddik 72c1928dc9 refactor: move widthClasses.class to the container div 2026-03-15 17:34:31 +00:00
Johannes Gäßler ae40cd27c8
CUDA: limit number of FA stream-k CUDA blocks (#20586) 2026-03-15 18:30:47 +01:00
Imad Saddik 0cd953eea2 chore: update webui build output 2026-03-15 17:13:14 +00:00
Imad Saddik 6074619ba4 style: restore class for checkbox labels 2026-03-15 17:11:58 +00:00
Imad Saddik 297abf8450 chore: update webui build output 2026-03-15 17:09:59 +00:00
Imad Saddik d4034eff07 fix: update chatWidthClasses to use autoChatWidth configuration 2026-03-15 17:08:43 +00:00
Imad Saddik b73209694d chore: update webui build output 2026-03-15 17:03:58 +00:00
Imad Saddik 2630c27754 refactor: simplify chatWidthClasses getter logic and remove widthClasses.class 2026-03-15 17:02:41 +00:00
Imad Saddik 1a6f21f25c chore: revert package-lock.json to match master 2026-03-15 16:56:41 +00:00
Imad Saddik 95be04617e chore: update webui build output 2026-03-15 16:56:08 +00:00
Imad Saddik 2836834801 refactor: remove anything related to the custom chat width setting 2026-03-15 16:54:43 +00:00
Imad Saddik 20a8227933 chore: update webui build output 2026-03-15 16:44:35 +00:00
Imad Saddik 89647d5daf chore: downgrade @lucide/svelte version and remove custom chat width component 2026-03-15 16:43:18 +00:00
Pascal ceef6b5233
ggml: avoid creating CUDA context during device init (#20595) 2026-03-16 00:42:56 +08:00
Adrien Gallouët 07c6a59b4f
vendor : update cpp-httplib to 0.38.0 (#20578) 
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
 2026-03-15 17:30:06 +01:00
MoonShadow 8b7d340b6f
ggml/hip: fix APU compatibility - soft error handling for hipMemAdviseSetCoarseGrain (#20536) 
* ggml/hip: fix APU compatibility - soft error handling for hipMemAdviseSetCoarseGrain

On AMD APU/iGPU devices (unified memory architecture), hipMemAdviseSetCoarseGrain
returns hipErrorInvalidValue because the hint is not applicable to UMA systems.
The previous CUDA_CHECK() call treated this as a fatal error, causing crashes on
APU systems such as AMD Strix Halo (gfx1151).

Fix: treat hipMemAdviseSetCoarseGrain as an optional performance hint - call it
without error checking and clear any resulting error with hipGetLastError().

Also add pre-allocation debug logging (GGML_LOG_DEBUG) to help diagnose memory
issues on APU systems, and store totalGlobalMem in device info.

Context: AMD APUs on Windows are affected by a ROCm runtime bug that limits
hipMallocManaged to ~64GB regardless of available system RAM. A fix has been
submitted upstream: https://github.com/ROCm/rocm-systems/pull/4077

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* ggml/hip: remove unrelated changes, keep only hipMemAdviseSetCoarseGrain fix

---------

Co-authored-by: moonshadow-25 <moonshadow-25@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-15 17:23:58 +01:00
Eric Hsieh 559646472d
fix: prevent nullptr dereference (#20552) 2026-03-15 16:51:49 +01:00
Sigbjørn Skjæret cf45437d35
codeowners : use teams (#20526) 
* use teams

* update

* update

* update

* update

* update
 2026-03-15 14:26:10 +01:00
Georgi Gerganov 9cd4ebcfb1
ci : split build.yml + server.yml (#20546) 
* ci : split build.yml

* cont : split server.yml

* cont : reduce paths

* cont : split build-android.yml + update paths

* ci : make msys workflows manual (#20588)

* ci : make cross-build workflows manual (#20585)

* cont : fix release paths

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-03-15 15:11:17 +02:00
Sigbjørn Skjæret 89d0aec042
convert : support contiguous method on lora tensors (#20489) 2026-03-15 12:15:12 +01:00
Bartowski b9da4444df
ggml : guard against sumq2 being 0 in IQ4_NL (#20460) 2026-03-15 10:47:28 +02:00
PikaPikachu 617db241aa
cuda : add RDNA4-specific MMVQ parameter table for bs=1 decode (#19478) 
* mmvq: add RDNA3/RDNA4-specific parameter table (nwarps=8, rows=1)

* mmvq: add dedicated RDNA3 parameter table

* mmvq: exclude RDNA3.5 (gfx1150/1151) from RDNA3 table
 2026-03-15 08:33:39 +01:00
Ruben Ortlam 1a3d8edbba
vulkan: use graphics queue on AMD (#20551) 
* vulkan: use graphics queue on AMD for slightly better performance

* disable async transfer queue on AMD
 2026-03-15 08:18:54 +01:00
sprayandwipe 6b10a82c00
kv-cache : fix reading llama_kv_cell_ext during state read (#20273) 
Co-authored-by: sid <sid@ragingfist.net>
 2026-03-15 09:11:19 +02:00
Michael Wand d23355afc3
model : wire up Qwen3.5/Qwen3.5MoE tensors for NVFP4 support (#20506) 2026-03-14 22:44:42 +01:00
Georgi Gerganov b30a5fdf37
metal : add FA specialization for HSK = 320, HSV = 256 (#20549) 2026-03-14 23:15:47 +02:00
Georgi Gerganov b4768955c4
ci : move self-hosted workflows to separate files (#20540) 2026-03-14 23:15:35 +02:00
Gerard Guillemas Martos fc350fdf96
docker : force Python 3.13 in Vulkan container (#20530) 
* ci: force Python 3.13 in Vulkan container

* remove unnecessary `update-alternatives` line
 2026-03-14 21:37:09 +01:00
Eve 3a6f059909
ci : try to optimize some jobs (#20521) 
* force arm version to test

* run on either x86 or arm if we can help it, this only works for runs without ccache

* readd other jobs

* remove ccache
 2026-03-14 20:27:52 +01:00
Max Krasnyansky 609ea50026
hexagon: Q4_0 and MXFP4 repack fixes (#20527) 
* hexagon: fix tail corruption with rows sizes not multiple of 256

* hexagon: use different stride for repacking partial blocks

* hex-mm: update repack and kernels to avoid shuffles for full 256-element blocks

Previous commit changed the repacking to use even:odd (0:1,2:3,..) packing
instead of the original (0:128,1:129,...) packing in order to fix tail corruption.
Since the mm kernels already deal with partial tails we can use even:odd
packing only for the last block.
This avoid performance penalty of having to shuffle to zip the elements
in the common case.

* hex-mm: update rmpy x8 for better optimizations

* hex-mm: tighten supported MUL_MAT checks to avoid spurios failures

* hex-mm: use vzero to init accumulators

* hex-mm: properly call partial rmpy_x8
 2026-03-14 11:09:08 -07:00
Georgi Gerganov 9f774e45ee
ci : reduce webgpu tests timeout to 900s (#20538) 
[no ci]
 2026-03-14 17:08:26 +02:00
Xuan-Son Nguyen 94d0262277
mtmd: add llama-mtmd-debug binary (#20508) 
* mtmd: add llama-mtmd-debug binary

* adapt

* fixes

* fix compile error

* fix windows compile error

* rm legacy clip_debug_encode()

* add MTMD_API to fix build
 2026-03-14 15:52:29 +01:00
Neo Zhang a93c0ef0fa
add op gated_delta_net (#20455) 2026-03-14 22:01:57 +08:00
Chedrian07 710878a7dd
webui: restore code preview iframe origin isolation (#20477) 2026-03-14 11:28:28 +01:00
Adrien Gallouët 0685848bc6
scripts : remove get-wikitext-103.sh (#20543) 
It doesn't work and no one seems to use it.

    $ wget https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-103-raw-v1.zip
    HTTP request sent, awaiting response... 301 Moved Permanently
    Location: unspecified
    ERROR: Redirection (301) without location.

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
 2026-03-14 11:22:04 +01:00