Pascal [Mon, 22 Jun 2026 08:55:28 +0000 (10:55 +0200)]
server: fix edit_file crash on append at end of file (line_start -1) (#24893)
line_start -1 normalized to n+1, so append inserted at lines.begin() + n + 1,
one past end() -> heap-buffer-overflow in vector::_M_range_insert.
Normalize -1 to n (insert at end()), restrict -1 to append mode and reject it
for replace/delete instead of silently clobbering the last line. Parenthesize
the insert offset so empty-file append computes the position as int first,
avoiding a transient begin() - 1 on a null vector data pointer.
make_utf8_argv rebuilds argv from GetCommandLineW to fix utf8 handling of
non ascii arguments on windows. the override runs unconditionally inside
common_params_parse, so it also clobbers a programmatic argv passed by a
caller. test-arg-parser builds a synthetic argv but then sees the real
process command line instead, the model argument is never parsed, and the
assert that expects success aborts via fastfail (0xC0000409). this shows up
as a random failure in the openvino windows workflow.
only override argv when its length matches the caller argc, so the utf8
repair still applies to real binaries while a programmatic argv stays intact.
davidrhodus [Sat, 20 Jun 2026 10:48:24 +0000 (03:48 -0700)]
model : glm-dsa load DSA indexer tensors as optional (#24770)
GLM-5.2 ships the DSA "lightning indexer" on only a subset of layers (the
"full" layers; others omit it), but the GLM_DSA loader created the five
indexer tensors on every layer as required, so loading any GLM-5.2 GGUF
failed with e.g. `missing tensor 'blk.3.indexer.k_norm.weight'`.
GLM_DSA's graph is llama_model_deepseek2::graph (plain MLA) and does not use
the indexer tensors (indexer runtime not yet implemented), so they are
loaded-but-unused. Marking them TENSOR_NOT_REQUIRED lets layers without an
indexer load as nullptr and the model runs as full MLA attention.
DeepSeek-V3.2 (uniform indexer on all layers) is unaffected.
Georgi Gerganov [Fri, 19 Jun 2026 06:22:34 +0000 (09:22 +0300)]
server : consolidate slot selection into get_available_slot (#24755)
Absorb get_slot_by_id logic into get_available_slot so slot selection
is handled by a single function call. When a specific slot id is
requested, the LCP similarity check still runs to enable proper
prompt cache updates.
shalinib-ibm [Fri, 19 Jun 2026 05:55:38 +0000 (11:25 +0530)]
ggml-cpu: support K tails in power10 Q8/Q4 MMA matmul (#24753)
* ggml-cpu: support K tails in Power10 MMA Q8/Q4 matmul
This patch removes the requirement that K be divisible by kc in the tinyBlas_Q0_PPC tiled matmul path. Process the final K panel using its actual depth and pass the reduced panel size through packing and kernel execution. This allows more workloads to use the MMA kernel and reduces fallback to mnpack.
Reguna [Thu, 18 Jun 2026 20:01:24 +0000 (04:01 +0800)]
server: add "X-Accel-Buffering": "no" header to streaming endpoints (#24774)
* server: add "X-Accel-Buffering": "no" header to streaming endpoints
This header tells Nginx (as a reverse proxy) to NOT buffer responses. (only affects streaming endpoints)
Without it, Nginx will break streaming with certain applications (notably the Pi coding harness).
Amos Wong [Thu, 18 Jun 2026 11:14:20 +0000 (19:14 +0800)]
ui: provide touch accessible model selection UI (#24604)
* ui : add model selector storybook stories
Covers list, favorites, single-model, all status states
(loading/loaded/sleeping/failed/idle), and selection states.
* ui : improve model selector mobile UX with hover media queries
Use @media (hover:none) to show action buttons directly on touch
devices and color-code them by model status (amber=sleeping,
green=loaded, muted=idle). Status dots hidden on touch. Desktop
hover behavior unchanged.
Anuj Attri [Thu, 18 Jun 2026 10:49:14 +0000 (06:49 -0400)]
server : return HTTP 400 on invalid grammar (#24144) (#24154)
Throw on grammar parse failure so the server returns HTTP 400
instead of silently dropping the constraint.
Add a regression test for the invalid-grammar response.
shalinib-ibm [Wed, 17 Jun 2026 18:45:19 +0000 (00:15 +0530)]
ggml-cpu: Conditionally enable power11 backend based on compiler support (#24687)
* ggml: Conditionally enable power11 backend based on compiler support
Guard POWER11 backend creation behind a compiler flag check for -mcpu=power11. This avoids build failures on current GCC/Clang toolchains while preserving forward compatibility once POWER11 support becomes available.
Georgi Gerganov [Wed, 17 Jun 2026 16:38:55 +0000 (19:38 +0300)]
metal : add f16 and bf16 support for concat operator (#24724)
* metal : add f16 and bf16 support for concat operator
Extend the Metal backend concat operator to support f16 and bf16 tensor
types in addition to the existing f32 and i32 support.
- Template kernel_concat on type T with specializations for float, half,
bfloat, and int
- Add type-specific pipeline getter ggml_metal_library_get_pipeline_concat()
- Update device support check to allow f16 unconditionally and bf16 when
device supports bfloat16
- Update dispatch to select the correct kernel specialization by type
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* metal : extend concat operator to support f16, bf16, i8, i16 and i64
Julien Chaumond [Wed, 17 Jun 2026 11:25:47 +0000 (13:25 +0200)]
webui: export conversations as jsonl (#24688)
* webui: export conversations as jsonl
each session is one jsonl file, a session header line followed by one line per message
exporting multiple conversations bundles them into a zip, one jsonl file each
* webui: import jsonl and zip conversation exports
parse the new jsonl session format and zip archives on import
keep supporting the legacy json format
* update stateful_kv_size correctly in mismatch case
* OpenVINO backend: enable arch test for qwen3vl
* OpenVINO backend: enable cohere2 for arch test
* OpenVINO backend: enable t5 for arch test
* OpenVINO backend: enable jamba for arch test
* OpenVINO backend: remove warning for tmp
* OpenVINO backend: enable kimi-linear for arch test
* Remove unused
* Fix gpt-oss accuracy issue
* OpenVINO backend: enable arctic for arch test
* OpenVINO backend: enable grok for arch test
* Gemma4 initial npu support (#179)
* Initiall gemma4 npu support
* temp. fix for gemma4 accuracy bug on npu
* Remove hardcoded names for npu-fold handling
* revert static n tokens for cont translation as it is not needed
* removed unused variable
* ggml-openvino: add GGML_OPENVINO_ENABLE_CACHE env var to control decoder cache. Add environment variable GGML_OPENVINO_ENABLE_CACHE (default: YES). When set to NO, the decoder_cache is bypassed and models are rebuilt from the cgraph on every inference call in both dynamic and static compute paths. This is useful for debugging and verifying correctness without caching interference.
* OpenVINO backend: fallback FLASH_ATTN_EXT in gemma3n to CPU backend
* Add raw ov infer profiling metric
* Add OV raw infer time metric to static compute path
Co-authored-by: virajwad <redacted>
* Modify precision of static profiling
* update to OV 2026.2, add OV windows CI
* fix editorconfig-checks
* Initiall gemma4 npu support
* temp. fix for gemma4 accuracy bug on npu
* Remove hardcoded names for npu-fold handling
* revert static n tokens for cont translation as it is not needed
* removed unused variable
* test-llama-archs fix
* Fix gemma4 flash_attn fallback
* support im2col
* fix code style
* disable add_rope_sin_cos optimization
* stateless boradcast and rope optimizations
* Enable manual gqa attn by default for stateless gpu
* manual gqa: fixed static batch
* gemma4 llama-bench ctx update fix
* Update OV win CI
* stateful rope fusion temp. fix
* OpenVINO backend: Conslolidate supported ops
* Exclude unsupported GGML_OP_SUB cases
* Exclude unsupported TOPK_MOE cases
* OpenVINO Backend: MUL_MAT enhancements
* Update OV CI
* support f16 mask input for npu
* Make GGML_OPENVINO_* env vars usage uniform
Standardize all GGML_OPENVINO_* env flags:
positive integers >0 to enable. Unset, empty, =0, or non-numeric values to disable.
This fixes cases where text values or empty strings enabled features.
* OpenVINO backend: Enhance envvar handling
* more cleanup
* move ggml_openvino_env_flag to appropriate place
Francois Dugast [Wed, 17 Jun 2026 05:54:21 +0000 (07:54 +0200)]
sycl: Add optional USM system allocations (#22526)
This introduces an optional feature to allocate large GPU buffers (≥ 1GB)
using USM system allocations if supported by the device. It allows using
buffers from the system allocator then letting the system manage memory
migrations between host and device as necessary.
This feature is disabled by default and requires the GGML_SYCL_USM_SYSTEM
environment variable to enable. If USM system allocations are not supported
by the device or the system, we fallback to regular allocations.
This feature can allow VRAM overcommit. For example, the test below fails
on B580 due to lack of memory for allocation, but it passes when enabling
USM system allocations:
Pascal [Tue, 16 Jun 2026 12:14:22 +0000 (14:14 +0200)]
ui: add source toggle to mermaid and svg blocks (#24652)
* ui: add source toggle to mermaid and svg blocks
Add a toggle button next to copy and preview that switches a rendered
mermaid or svg block to its source code and back. The button is shared by
both block types and the rendered view stays the default.
The source view reuses the code block scroll container and the highlighted
code element captured at transform time, so it matches the app code blocks
without highlighting again.
Make tall diagrams scroll like text code blocks: safe centering keeps the
diagram centered when it fits and falls back to start alignment when it
overflows, so the top stays reachable instead of clipping above.
Keep the block header opaque and layered above the scrolled diagram, and
ignore header clicks in the zoom handler, so a button click never falls
through to the zoom dialog.
* ui: transparent diagram block header, address review from @allozaur
Oliver Simons [Tue, 16 Jun 2026 09:52:38 +0000 (11:52 +0200)]
Fix and restrict NVFP4 edge-cases in llama-graph (#24331)
* Move post-GEMM MUL required for dequant b4 lora and bias add
see https://github.com/ggml-org/llama.cpp/pull/23484 :
1. For lora, I would presume we want fully dequantized values before
doing the residuals, but this depends on how the LORAs were
generated. Literature tells me LORA happens post-mul but pre-bias add https://github.com/ggml-org/llama.cpp/pull/8332
2. For ModelOPT, bias-add should happen on [fully-dequantized
values](https://github.com/NVIDIA/Model-Optimizer/blob/b49f9b9e2d747af992d78a3aa7f10efe5a8847e1/modelopt/torch/quantization/backends/nvfp4_gemm.py#L59-L64)
* Restrict build_ffn for NVFP4 to supported combinations
overview / pkg / ggml / sources / llama.cpp / log