Pascal [Wed, 10 Dec 2025 21:18:21 +0000 (22:18 +0100)]
server: add presets (config) when using multiple models (#17859)
* llama-server: recursive GGUF loading
Replace flat directory scan with recursive traversal using
std::filesystem::recursive_directory_iterator. Support for
nested vendor/model layouts (e.g. vendor/model/*.gguf).
Model name now reflects the relative path within --models-dir
instead of just the filename. Aggregate files by parent
directory via std::map before constructing local_model
* server : router config POC (INI-based per-model settings)
* server: address review feedback from @aldehir and @ngxson
PEG parser usage improvements:
- Simplify parser instantiation (remove arena indirection)
- Optimize grammar usage (ws instead of zero_or_more, remove optional wrapping)
- Fix last line without newline bug (+ operator instead of <<)
- Remove redundant end position check
Feature scope:
- Remove auto-reload feature (will be separate PR per @ngxson)
- Keep config.ini auto-creation and template generation
- Preserve per-model customization logic
Complete rewrite of INI parser grammar and visitor:
- Use p.chars(), p.negate(), p.any() instead of p.until()
- Support end-of-line comments (key=value # comment)
- Handle EOF without trailing newline correctly
- Strict identifier validation ([a-zA-Z_][a-zA-Z0-9_.-]*)
- Simplified visitor (no pending state, no trim needed)
- Grammar handles whitespace natively via eol rule
Business validation preserved:
- Reject section names starting with LLAMA_ARG_*
- Accept only keys starting with LLAMA_ARG_*
- Require explicit section before key-value pairs
Children now receive minimal CLI args (executable, model, port, alias)
instead of inheriting all router args. Global settings pass through
LLAMA_ARG_* environment variables only, eliminating duplicate config
warnings.
Fixes: Router args like -ngl, -fa were passed both via CLI and env,
causing 'will be overwritten' warnings on every child spawn
* add common/preset.cpp
* fix compile
* cont
* allow custom-path models
* add falsey check
* server: fix router model discovery and child process spawning
- Sanitize model names: replace / and \ with _ for display
- Recursive directory scan with relative path storage
- Convert relative paths to absolute when spawning children
- Filter router control args from child processes
- Refresh args after port assignment for correct port value
- Fallback preset lookup for compatibility
- Fix missing argv[0]: store server binary path before base_args parsing
* Revert "server: fix router model discovery and child process spawning"
Rhys-T [Tue, 9 Dec 2025 11:17:41 +0000 (06:17 -0500)]
cmake: fix Mach-O current version number (#17877)
PR #17091 set the VERSION of various libraries to 0.0.abcd, where abcd
is the LLAMA_BUILD_NUMBER. That build number is too large to fit in the
Mach-O 'current version' field's 'micro' part, which only goes up to
255. This just sets the Mach-O current version to 0 to get it building
properly again.
- Add KEY_CTRL_ARROW_LEFT and KEY_CTRL_ARROW_RIGHT codes
- Windows: detect CTRL modifier via dwControlKeyState
- Linux: parse ANSI sequences with modifier (1;5D/C)
- Implement move_word_left/right with space-skipping logic
- Refactor escape sequence parsing to accumulate params
* console: add Delete key support
- Windows: VK_DELETE detection
- Linux: ESC[3~ sequence parsing
- Forward character deletion with UTF-8 support
* console: implement bash-style history editing
- Edit any history line during UP/DOWN navigation, edits persist
- Pressing Enter appends edited version as new history entry
- Original line stay untouched in their positions
Chenguang Li [Tue, 9 Dec 2025 09:53:23 +0000 (17:53 +0800)]
CANN: add support for partial RoPE and Vision mode (#17543)
* cann: add support for partial RoPE and Vision mode
Add support for two important RoPE variants: partial rotation (rope_dims < ne0)
and Vision mode rotation.
1. Support for partial RoPE (rope_dims < ne0):
- Split tensor into head (first rope_dims dimensions) and tail portions
- Apply rotation only to head portion using RotaryPositionEmbedding operator
- Copy unrotated tail portion directly from source to destination
- Handle both contiguous and non-contiguous tensor layouts
2. Support for Vision mode (GGML_ROPE_TYPE_VISION):
- Set rope_dims = ne0 for Vision mode to rotate entire tensor
- Vision mode pairs dimension i with dimension i+n_dims (where n_dims = ne0/2)
- No tail handling needed since entire tensor is rotated
Implementation details:
- Use has_tail flag to determine execution path: head/tail splitting when
rope_dims < ne0, or full tensor rotation when rope_dims == ne0
- Support both F32 and F16 data types with intermediate F32 conversion
- Copy non-contiguous tensors to contiguous buffers before calling
RotaryPositionEmbedding operator for compatibility
- Improve cache invalidation logic to include rope_dims and indep_sects
parameters
These enhancements enable CANN backend to handle various RoPE configurations
used in modern vision-language models and models with partial rotation.
wsbagnsv1 [Mon, 8 Dec 2025 09:41:08 +0000 (10:41 +0100)]
cuda: optimize SOLVE_TRI using registers and FMAF (#17703)
* ggml-cuda: optimize solve_tri_f32_fast and fix stride handling
- Switch from using shared memory for the RHS/solution matrix to a register-based approach (x_low, x_high), reducing shared memory pressure and bank conflicts.
- Implement explicit `fmaf` instructions for the reduction loop.
- Update kernel arguments to pass strides in bytes rather than elements to align with standard ggml tensor arithmetic (casting to `char *` before addition).
- Remove unused `MAX_K_FAST` definition.
* Small cleanup
* Remove comments in solve_tri.cu
* Update ggml/src/ggml-cuda/solve_tri.cu
Co-authored-by: Johannes Gäßler <redacted>
* Update ggml/src/ggml-cuda/solve_tri.cu
Co-authored-by: Johannes Gäßler <redacted>
* Update ggml/src/ggml-cuda/solve_tri.cu
Co-authored-by: Johannes Gäßler <redacted>
* Use const for variables in solve_tri.cu
Jeff Bolz [Sat, 6 Dec 2025 17:46:46 +0000 (11:46 -0600)]
vulkan: perf_logger improvements (#17672)
* vulkan: perf_logger improvements
- Move perf_logger from device to ctx.
- Add an env var to control the frequency we dump the stats. If you set a very
large value, it just dumps when the ctx is destroyed.
- Add a fusion info string to the tracking, only log one item per fused op.
- Fix MUL_MAT_ID flops calculation.
Daniel Bevenius [Sat, 6 Dec 2025 11:26:20 +0000 (12:26 +0100)]
llama : remove quantization sanity check (#17788)
* llama : remove quantization sanity check
This commit removes the quantization sanity check for attention layers.
The motivation for this is that there are model that are hybrid models
that have recurrent layers, experts layers, and attention layers. For
these models the current check fails as the experts layers are not
taking into account. After consideration, it was decided that this check
is not strictly necessary, and can be removed to allow for more flexible
model architectures.
* llama : remove unused pruned_attention_w and is_clip_model vars
Jeff Bolz [Sat, 6 Dec 2025 10:12:26 +0000 (04:12 -0600)]
vulkan: Use one row per workgroup for f32 mmv (#17711)
The MoE models have a mul_mat_vec with very small m (32, 64, 128) right before
the topk_moe selection. Running multiple rows per wg doesn't utilize the SMs
well. I think even for larger m, f32 is so bandwidth-limited that running
multiple rows doesn't help.
Jeff Bolz [Fri, 5 Dec 2025 21:03:19 +0000 (15:03 -0600)]
vulkan: fix top_k bug when there are ties in the input (#17659)
* vulkan: Reduce temporary memory usage for TOP_K
- Compute row size for the temp buffer based on the output of the first pass.
- Update shader addressing math to use the output row size
- Pass the output row size as "ncols_output", what used to be "ncols_output" is now "k"
For the common case of K=40 and src0=(200000,1,1,1), this reduces the temporary buffer
from about 3.2MB to 500KB.
* vulkan: fix top_k bug when there are ties in the input
I noticed by inspection a bug in the vulkan top_k shader where if the least
value in the top_k appears multiple times we could end up writing those extra
copies out rather than some larger values (if the larger values are on higher
numbered threads).
I rewrote the test verification to handle this case, where the final index set
is not necessarily the same.
* Update tests/test-backend-ops.cpp
Co-authored-by: Georgi Gerganov <redacted>
---------
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.
neg f16xf32xip builds and runs, havent actually ran a model that uses neg kernel yet though
Co-authored-by: James Contini <redacted> Co-authored-by: Neha Abbas <redacted> Co-authored-by: Abhijit Ramesh <redacted>
* Remove extra code and format
Gabe Goodhart [Thu, 4 Dec 2025 17:12:19 +0000 (10:12 -0700)]
metal: TRI, FILL, EXPM1, SOFTPLUS (#16623)
* feat(wip): Port initial TRI impl from pervious work
The kernel does not work and is not optimized, but the
code compiles and runs, so this will be the starting point
now that the core op has been merged.
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* fix: Remove argument for constant val override
This was added in the original draft, but later removed. With this, the
kernel now passes tests.
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* feat: Move the ttype conditional to templating to avoid conditional in kernel
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* fix: Type fixes
Signed-off-by: Gabe Goodhart <redacted> Co-authored-by: Georgi Gerganov <redacted> Co-authored-by: Georgi Gerganov <redacted>
* feat: Add softplus for metal
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* feat: Add EXPM1 for metal
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* feat: Add FILL for metal
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* refactor: Branchless version of tri using _ggml_vec_tri_cmp as a mask
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* fix: Remove unused arguments
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
* refactor: Use select instead of branch for softplus non-vec
Branch: ggml-cumsum-tri
Signed-off-by: Gabe Goodhart <redacted>
---------
Signed-off-by: Gabe Goodhart <redacted> Co-authored-by: Georgi Gerganov <redacted>
Daniel Bevenius [Thu, 4 Dec 2025 12:36:50 +0000 (13:36 +0100)]
common : skip model validation when --help is requested (#17755)
This commit skips the model validation check when the user specifies the
--help option.
The motivation for this is that currently and error is thrown before the
--help could be processed. Now skips validation if params.usage is set,
allowing help to display without requiring --model.
Adrien Gallouët [Thu, 4 Dec 2025 10:42:13 +0000 (11:42 +0100)]
cmake : simplify build info detection using standard variables (#17423)
The current approach has several drawbacks. Mostly, when
cross-compiling, invoking the compiler binary directly to query the
machine hardware can behave unexpectedly depending on the toolchain
wrapper (using COMPILER_TARGET, CFLAGS, etc).
As CMake is the official tool to build llama.cpp, I propose to only rely
on it to get those variables (`CMAKE_SYSTEM_NAME` and
`CMAKE_SYSTEM_PROCESSOR`).
overview / pkg / ggml / sources / llama.cpp / log