dddca026bf
webui: add model information dialog to router mode ( #20600 )
...
* webui: add model information dialog to router mode
* webui: add "Available models" section header in model list
* webui: remove nested scrollbar from chat template in model info dialog
* chore: update webui build output
* feat: UI improvements
* refactor: Cleaner rendering + UI docs
* chore: update webui build output
---------
Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com >
2026-03-16 15:38:11 +01:00
3c8521c4f5
llama-graph: replace cont with reshape for alpha in qwen35 ( #20640 )
2026-03-16 22:07:13 +08:00
6c8c55afb5
PR cleanup
2026-03-16 21:04:16 +08:00
feea014774
sd: support for dynamic LoRA loading from a directory ( #2036 )
...
* backend support for controlling LoRA cache and fixed multipliers
The generation LoRA multipliers are now added to the initial
multipliers, so e.g. a merged LCM model will behave the same as
a normal model with a preloaded LCM LoRA.
* frontend support
2026-03-16 20:39:21 +08:00
67a2209fab
webui: Add MCP CORS Proxy detection logic & UI ( #20167 )
...
* refactor: MCP store cleanup
* feat: Add MCP proxy availability detection
* fix: Sidebar icon
* chore: update webui build output
* chore: Formatting
* chore: update webui build output
* chore: Update package lock
* chore: update webui build output
* chore: update webui build output
* chore: update webui build output
2026-03-16 13:05:36 +01:00
d65c4f2dc9
Fix model selector locked to first loaded model with multiple models ( #20580 )
...
* webui: fix model selector being locked to first loaded model
When multiple models are loaded, the auto-select effect would re-fire
on every loadedModelIds change, overriding the user's manual model
selection. Guard with selectedModelId so auto-select only kicks in
when no model is chosen yet.
* chore: update webui build output
2026-03-16 12:04:06 +01:00
d8c331c0af
webui: use date in more human readable exported filename ( #19939 )
...
* webui: use date in exported filename
Move conversation naming and export to utils
update index.html.gz
* webui: move literals to message export constants file
* webui: move export naming and download back to the conversation store
* chore: update webui build output
* webui: add comments to some constants
* chore: update webui build output
2026-03-16 11:18:13 +01:00
46dba9fce8
vulkan: fix flash attention dot product precision ( #20589 )
2026-03-16 10:45:49 +01:00
b88fc44d0e
add some debug prints
2026-03-16 16:27:49 +08:00
de8f01c2d7
model : wire up Nemotron-H tensors for NVFP4 support ( #20561 )
...
* wire up Nemotron-H tensors for NVFP4 support
* add ssm tensors
* alignment
2026-03-16 09:19:16 +01:00
079e5a45f0
convert : support mixed-precision ModelOpt models with per-tensor NVFP4/FP8 quantization ( #20539 )
...
* support mixed-precision ModelOpt models with per-tensor NVFP4/FP8 quantization
* cleanup
* fallback
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
2026-03-16 09:18:47 +01:00
d3936498a3
common : fix iterator::end() dereference ( #20445 )
2026-03-16 08:50:38 +02:00
34818ea6c0
CUDA: GDN hide memory latency ( #20537 )
2026-03-16 11:41:45 +08:00
9e2e2198b0
tools/cli: fix disable reasoning ( #20606 )
2026-03-15 22:40:53 +01:00
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
ebbf544ed1
sycl : fix for untransposed GDA recurrent state ( #20583 )
2026-03-15 19:10:15 +01:00
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
ae40cd27c8
CUDA: limit number of FA stream-k CUDA blocks ( #20586 )
2026-03-15 18:30:47 +01:00
ceef6b5233
ggml: avoid creating CUDA context during device init ( #20595 )
2026-03-16 00:42:56 +08:00
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
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
559646472d
fix: prevent nullptr dereference ( #20552 )
2026-03-15 16:51:49 +01:00
310bd97972
router mode is fully functional
2026-03-15 23:07:47 +08:00
fc3399cdc8
reduce some log spam
2026-03-15 22:45:50 +08:00
5a65005d27
allow swap back to initial model
2026-03-15 21:35:23 +08:00
cf45437d35
codeowners : use teams ( #20526 )
...
* use teams
* update
* update
* update
* update
* update
2026-03-15 14:26:10 +01:00
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
2093ca4c73
ace step optimizations
2026-03-15 20:58:45 +08:00
89d0aec042
convert : support contiguous method on lora tensors ( #20489 )
2026-03-15 12:15:12 +01:00
ccd4745e0c
ollama streaming emulation
2026-03-15 18:25:37 +08:00
2e725e4f10
fixed port bug
2026-03-15 17:00:50 +08:00
b9da4444df
ggml : guard against sumq2 being 0 in IQ4_NL ( #20460 )
2026-03-15 10:47:28 +02:00
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
b437d18319
add support for cache modes to accelerate image generation ( #2021 )
...
* sd: sync to master-525-d6dd6d7
* sd: add support for cache modes for inference acceleration
* keep gendefaults as a JSON object inside the config file
* covered more invalid cases on gendefaults parsing
2026-03-15 15:27:14 +08:00
893b8abc21
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/vulkan.Dockerfile
# .github/workflows/build-cache.yml
# .github/workflows/build-cmake-pkg.yml
# .github/workflows/build-linux-cross.yml
# .github/workflows/build.yml
# .github/workflows/release.yml
# .github/workflows/server-self-hosted.yml
# .github/workflows/server-webui.yml
# ggml/src/ggml-hexagon/ggml-hexagon.cpp
# ggml/src/ggml-hexagon/htp/matmul-ops.c
# tests/test-backend-ops.cpp
2026-03-15 15:20:38 +08:00
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
f579939057
updated lite, change smartcache snapshot behavior to conserve slots
2026-03-15 15:15:39 +08:00
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
fcdf2f40d5
no need snapshot after gen is complete.
2026-03-15 12:34:48 +08:00
33211e6edf
timing measure fixes
2026-03-15 12:23:14 +08:00
8f63e0e2fd
Merge remote-tracking branch 'spray/fix/n_pos_per_embd' into concedo_experimental
2026-03-15 12:12:41 +08:00
f3d2f58fa8
note: smartcache is broken for rnn currently
2026-03-15 11:31:47 +08:00
b1c500ae2b
Merge commit '2948e6049a4ad0f96a4ab15246db2d2086b80703' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CONTRIBUTING.md
# docs/backend/VirtGPU/development.md
# docs/ops.md
# docs/ops/WebGPU.csv
# embd_res/templates/GigaChat3-10B-A1.8B.jinja
# embd_res/templates/GigaChat3.1-10B-A1.8B.jinja
# ggml/src/ggml-hip/CMakeLists.txt
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# scripts/sync_vendor.py
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-chat.cpp
# tests/test-grammar-integration.cpp
# tests/test-quantize-fns.cpp
2026-03-15 11:21:24 +08:00
67c9798d0b
Merge commit '3ca19b0e9f3f4f444d22c9f509805d037a611847' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# common/CMakeLists.txt
# common/chat-peg-parser.cpp
# docs/backend/SYCL.md
# docs/ops.md
# docs/ops/SYCL.csv
# ggml/src/ggml-sycl/common.hpp
# ggml/src/ggml-sycl/convert.hpp
# ggml/src/ggml-sycl/element_wise.cpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/norm.cpp
# ggml/src/ggml-sycl/rope.cpp
# ggml/src/ggml-sycl/rope.hpp
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
# ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.wgsl
# ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
# scripts/compare-llama-bench.py
# scripts/sync_vendor.py
# tests/CMakeLists.txt
# tools/cli/cli.cpp
2026-03-15 11:11:31 +08:00
d23355afc3
model : wire up Qwen3.5/Qwen3.5MoE tensors for NVFP4 support ( #20506 )
2026-03-14 22:44:42 +01:00
b30a5fdf37
metal : add FA specialization for HSK = 320, HSV = 256 ( #20549 )
2026-03-14 23:15:47 +02:00
b4768955c4
ci : move self-hosted workflows to separate files ( #20540 )
2026-03-14 23:15:35 +02:00
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
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
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
Pascal
Aman Gupta
Concedo
Wagner Bruna
Aleksander Grygier
Woof Dog
Ruben Ortlam
Sigbjørn Skjæret
Richard Davison
Masato Nakasaka
Piotr Wilkin (ilintar)
Georgi Gerganov
Johannes Gäßler
Adrien Gallouët
MoonShadow
Eric Hsieh
Bartowski
PikaPikachu
sprayandwipe
Michael Wand
Gerard Guillemas Martos
Eve
Max Krasnyansky