8ced5f41f9
Move to no timeout for WaitAny in graph submission to avoid deadlocks in some cases on llvm-pipe backends ( #20618 )
2026-03-18 10:23:47 -07:00
78d550b541
ggml-cpu/x86: fix unused changemask warning in repack ( #20692 )
2026-03-18 18:45:06 +02:00
4efd326e71
sync : ggml
2026-03-18 15:17:28 +02:00
b08f7322ee
ggml : bump version to 0.9.8 (ggml/1442)
2026-03-18 15:17:28 +02:00
79187f2fb8
ggml : restore ggml_type_sizef() to aboid major version bump (ggml/1441)
2026-03-18 15:17:28 +02:00
48e61238e1
webui: improve tooltip wording for attachment requirements ( #20688 )
...
* webui: improve tooltip wording for attachment requirements
Co-Authored-By: Claude <Agents+claude@huggingface.co>
* chore: update webui build output
* chore: update webui build output
---------
Co-authored-by: Claude <Agents+claude@huggingface.co>
2026-03-18 14:01:02 +01:00
312cf03328
llama : re-enable manual LoRA adapter free ( #19983 )
...
* Re-enable manual LoRA adapter free
* Remove stale "all adapters must be loaded before context creation" stale comments
2026-03-18 12:03:26 +02:00
f4049ad735
tests : fix test-jinja-py Windows failures by bypassing command-line args [no ci] ( #20483 )
...
* Fix errors occurring on Windows
* Reverted fix
#20365 will take care of CRLF isue
* Changed to write to directly to stdin
* Prevent fclose to happen twice
2026-03-18 10:43:31 +01:00
5e8910a0db
common : rework gpt-oss parser ( #20393 )
...
* common : rework gpt-oss parser
* cont : fix gpt-oss tests
* cont : add structured output test
* cont : rename final to final_msg
2026-03-18 10:41:25 +01:00
fe00a84b4b
tests: enable kv_unified to prevent cuda oom error on rtx 2060 ( #20645 )
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2026-03-18 17:40:22 +08:00
7ab321d40d
webui: Fix duplicated messages on q param ( #20715 )
...
* fix: Remove duplicate message sending on `?q` param
* chore: update webui build output
2026-03-18 10:32:43 +01:00
7533a7d509
HIP : ignore return of hipMemAdvise [no ci] ( #20696 )
2026-03-18 09:53:13 +01:00
a69d54f990
context : fix graph not resetting when control vector changes ( #20381 )
2026-03-18 08:10:13 +02:00
cf23ee2447
hexagon: add neg, exp, sigmoid, softplus ops, cont, repeat ops ( #20701 )
...
Add element-wise unary ops needed by Qwen 3.5's DeltaNet linear
attention layers. These ops follow the existing unary-ops pattern
with VTCM DMA double-buffering.
- neg: negate via scale by -1.0
- exp: uses existing hvx_exp_f32 HVX intrinsics
- sigmoid: uses existing hvx_sigmoid_f32_aa HVX intrinsics
- softplus: log(1 + exp(x)) scalar fallback
- CONT reuses the existing CPY infrastructure since making a tensor
contiguous is equivalent to a same-type copy.
- REPEAT implements tiled memory copy with multi-threaded execution via
the worker pool, supporting f32 and f16 types. The kernel parallelizes
across output rows and uses memcpy for each tile.
Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
2026-03-17 15:34:36 -07:00
892e3c333a
vulkan: disable mmvq on Intel Windows driver ( #20672 )
...
* vulkan: disable mmvq on Intel Windows driver
* improve comment
2026-03-17 21:51:43 +01:00
ee4801e5a6
ggml-blas: set mkl threads from thread context ( #20602 )
...
* ggml blas: set mkl threads from thread context
* add code to run blas locally
2026-03-18 01:16:49 +08:00
d2ecd2d1cf
common/parser: add `--skip-chat-parsing` to force a pure content parser. ( #20289 )
...
* Add `--force-pure-content` to force a pure content parser.
* Update common/arg.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Change parameter name [no ci]
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-03-17 16:16:43 +01:00
054d8b0f24
ggml-cpu: fix RVV checks in quants and repacking ( #20682 )
...
* ggml-cpu: refactor quants.c; add rvv check
* ggml-cpu: refactor; disable generic fallback
2026-03-17 16:03:40 +02:00
ab0bb93748
ci : bump ccache [no ci] ( #20679 )
...
* bump ccache
* forgotten
* disable for s390x
* disable also for ppc64le
2026-03-17 14:54:31 +01:00
3a5cb629b1
vulkan: async and event fixes ( #20518 )
...
* vulkan: fix event wait submission, event command buffer reset
* fix event command buffer reset validation error
* also reset command buffers before reuse
* use timeline semaphores instead of fences for event_synchronize
* don't use initializer list for semaphore wait info
* use multiple events to avoid reset issues
* fix event reuse issue with multiple vectors
* add semaphore wait condition also if compute_ctx already exists
* remove event pending stage
2026-03-17 14:27:23 +01:00
8cc2d81264
server : fix ctx checkpoint invalidation ( #20671 )
2026-03-17 15:21:14 +02:00
627670601a
kleidiai : fix MUL_MAT support for batched (3D) inputs ( #20620 )
...
* kleidiai : fix MUL_MAT support for batched (3D) inputs
The supports_op() check incorrectly rejected MUL_MAT operations with 3D
inputs (ne[2] > 1), but the actual compute_forward_qx() implementation
handles batched inputs correctly via a loop over ne12.
This caused models with Q4_0/Q8_0 weights to crash during graph scheduling
when n_seq_max > 1, because weights were placed in KLEIDIAI buffers during
loading (tested with 2D inputs) but the runtime used 3D inputs.
Also relax the buffer check to allow supports_op() to be called during
weight loading when src[0]->buffer is NULL.
Fixes #20608
* Kleidiai support_ops should only return true for 3D inputs, not also 4D
2026-03-17 14:03:54 +02:00
740a447fc3
vulkan: allow graphics queue only through env var ( #20599 )
...
* vulkan: avoid graphics queue on non-RADV AMD drivers
* avoid graphics queues on small GPUs
* change to only use graphics queue if overridden with env var GGML_VK_ALLOW_GRAPHICS_QUEUE
* reenable transfer queue if graphics queue is not used
2026-03-17 10:09:59 +01:00
b6c83aad55
[SYCL] ehance UPSCALE to support all UT cases ( #20637 )
...
* [SYCL] ehance UPSCALE to support more cases
* rm test case result of SYCL1
2026-03-17 10:01:52 +08:00
2e4a6edd4a
tools/server: support refusal content for Responses API ( #20285 )
...
* Support refusal content for Responses API
* Update tools/server/server-common.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update tools/server/server-common.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-03-17 01:42:04 +01:00
d34ff7eb5b
model: mistral small 4 support ( #20649 )
...
* model: mistral small 4 support
* fix test
* fix test (2)
* Apply suggestions from code review
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* change newline
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-03-17 00:31:14 +01:00
45172df4d6
ci : disable AMX jobs ( #20654 )
...
[no ci]
2026-03-16 22:38:59 +02:00
9b342d0a9f
benches : add Nemotron 3 Nano on DGX Spark ( #20652 )
...
[no ci]
2026-03-16 21:50:43 +02:00
55e87026f7
tests : write to binary buffer to avoid newline translation in jinja -py [no ci] ( #20365 )
2026-03-16 20:40:22 +01:00
cf21cdf36c
kleidiai: add data type check to get_tensor_traits ( #20639 )
...
* kleidiai: add data type check to get_tensor_traits
* Added check for F16 data type into get_tensor_traits path with input data
not in ggml_backend_cpu_kleidiai_buffer_type format (unsupported for Q4/8)
Signed-off-by: Martin Klacer <martin.klacer@arm.com>
Change-Id: I9aca4b9b8d669d35db6f1dbcc4e080b1919b1de7
* updated ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
updated kleidiai.cpp file as per suggestion
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Signed-off-by: Martin Klacer <martin.klacer@arm.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-03-16 21:25:54 +02:00
0ed992973b
ci : update labeler ( #20629 )
2026-03-16 20:24:20 +01:00
1bbec6a75d
jinja : add capability check for object args ( #20612 )
2026-03-16 17:43:14 +01:00
f47a246a08
sync : ggml
2026-03-16 17:22:06 +02:00
c0ccbd1f86
ggml : try fix arm build (whisper/0)
2026-03-16 17:22:06 +02:00
f6da02c3f2
ggml : extend im2col f16 (ggml/1434)
...
* examples/yolo: fix load_model memory leak
* fix/issue-1433 ggml_compute_forward_im2col_f16 assert error
* fix/issue-1433
2026-03-16 17:22:06 +02:00
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
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
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
Reese Levine
Shaw Nguyen
Georgi Gerganov
Julien Chaumond
Pop Flamingo
Masato Nakasaka
Aldehir Rojas
Aaron Teo
Aleksander Grygier
uvos
Andreas Obersteiner
Krishna Sridhar
Ruben Ortlam
Kevin Hannon
Piotr Wilkin (ilintar)
Taimur Ahmad
Sigbjørn Skjæret
Justin Bradford
Neo Zhang
Xuan-Son Nguyen
Martin Klacer
David366AI
Pascal
Aman Gupta
Woof Dog
Richard Davison
Johannes Gäßler