* Add arch support for cohere2-MoE
* Removed redundant gating_func checks
* Changed ffn lookup to prefer prefix_dense_intermediate_size
* Renamed arch to cohere2moe
* Removed redundant lmhead check and chat template changes
* Removed lm_head.weight check from modify tensors, load output tensor not required, fallback to token_embd.weight
* Changed to (routed+shared)*0.5 for shared expert combined avg
* fixed sliding_window_pattern issue and pattern
* Fixed transformers crash 'first_k_dense_replace' error
* Remove comment
* Removed cohere2-moe as a tokenizer type and kept as tiny_aya. Renamed North-Mini-Code-1.0.
* Fixed MTP fail, changed to use iSWA
* Fixed remaining todos: cohere2moe renamed, changed swa parsing to use get_key_or_arr, removed extra get_arr use
* Force metadata usage
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Remove Cohere2 checkpoint comment
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Remove MTP comment
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Regenerate cohere2moe tokenizer hash
* Add cohere2moe to Llama Model Saver supported list
* Check for zerobios tensors and add support for Command to use LayerNorm
* Map expert_selection_fn to sigmoid in base.py instead of command.py
* use bools for foundnorm/foundnormrms
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* vulkan: support non-contig unary/glu ops
Change unary/glu ops to pass in all strides and use fastdiv for the index
calculation. Put all unary ops in one file, similar to glu, to share the
code. codex went ahead and added expm1 without me asking, but I had to
make it do a real precision analysis rather than just making stuff up.
unary.comp initially couldn't use generic_unary_head because there wasn't
space for xielu's additional constants. Fixing this required packing the
fastdiv 'L' values.
* attempt to workaround compiler bug
* resolve conflict from #23991
* use expm1
* server: clean up static assets handling
* nits
* simplify file name handling, use static file name everywhere
* cmake/ui : bundle UI assets in an archive
* ui : run prettier on post-build.js
---------
Co-authored-by: Alde Rojas <hello@alde.dev>
When reasoning-budget is set in model.ini, the per-request
thinking_budget_tokens from the WebUI was ignored because the
model.ini value took unconditional precedence.
Swap the precedence so the WebUI per-request value is checked
first, with the model.ini value serving as a fallback default.
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* ui: bake jpeg exif orientation into uploaded images
stb_image in mtmd ignores exif metadata, so rotated smartphone photos
reach the model with raw pixel orientation. The webui now reads the
exif orientation tag at send time and feeds it into the existing
capImageDataURLSize canvas pass: the browser applies the rotation when
decoding, so capped images come out upright for free, and images under
the cap threshold get a single plain redraw when orientation > 1.
At most one re-encode ever happens per image. Upright jpegs with
capping disabled pass through untouched, bit perfect.
Adds jpeg-orientation.ts with a minimal exif parser working on a
bounded base64 prefix (both endianness, returns 1 on any malformed
input) and unit tests against handcrafted jpeg byte streams.
* ui: move jpeg exif constants into lib/constants
* ui: add browser test for jpeg orientation and capping
Covers capImageDataURLSize end to end in chromium with real Pillow
generated jpeg fixtures across exif orientations 1/3/5/6/8: upright
quadrant colors checked pixel-wise, expected dimensions with and
without capping, no orientation tag left in the output, and strict
passthrough when nothing needs rewriting.
* restore SYCL build and release, remove github cache
* modify for test only
* verify the ccache is used
* remove debug code change
* rm duplicate action, update key in ccache
* add action ccache-clear after building in both ubuntu and windows
* set %NUMBER_OF_PROCESSORS% in widnows build
* Make ggml_gated_delta_net take only the initial recurrent state (D, 1, n_seqs) and passes the snapshot count K as an op parameter instead of inferring it from state->ne[1].
Remove the padding hack and copy all emitted snapshots into the recurrent cache with a single strided ggml_cpy
* Make GDN changes in all backends. Address review comments.
* Fix CI build errors
This is a non-functional change.
When using `--spec-type ngram-map-k4v`, the log messages at startup and
runtime say `ngram-map-k`. Added logic in the in the constructor of
`common_speculative_impl_ngram_map_k` to pass the correct
`COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V` when `config.key_only` is
`false`.
After this change, the log messages use the correct name.
* webui: implement pinned conversations support
* webui: linter/prettier pass
* Fix the unused handleMobileSidebarItemClick from the component.
* the search should find pinned conversations as well
Co-authored-by: Pascal <admin@serveurperso.com>
---------
Co-authored-by: Pascal <admin@serveurperso.com>
* llama-graph : apply embedding scale when deepstack is not used
* nits: remove non-existant hunyuan-vl from the tests
* apply suggestion from @gabe-l-hart
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* ui: add opt-in run_javascript frontend tool
Expose a run_javascript tool to the model, executed entirely in the
browser through the existing agentic loop. Code runs in a Web Worker
inside a sandboxed iframe with an opaque origin, isolated from the
WebUI and its API. Console output, errors and the return value are
fed back as the tool result. The parent enforces a hard timeout by
removing the iframe, which terminates the worker.
Disabled by default, toggle in Settings > Developer.
* ui: address review feedback from allozaur
Use the JsonSchemaType enum for the tool definition parameter types
instead of raw string literals, extending it with STRING and NUMBER.
Move the worker shim and the iframe harness html into their own files
so the service no longer carries inline source blobs.
Replace the remaining magic strings with constants: SANDBOX_EMPTY_OUTPUT
and SANDBOX_TRUNCATION_NOTICE, and reuse NEWLINE_SEPARATOR for joins.
* ui: move sandbox worker shim to a raw imported file
Replace the inline worker template string with a real sandbox-worker.js
imported as raw text, and build the iframe harness from it in
sandbox-harness.ts. The raw worker ships as a string, not a module, so
it is excluded from eslint and the typecheck program.
* vulkan: add support for valve fp16 dot2 extension
* use macro for dot2 path choice
* properly check for the feature
* add dot_product abstraction to reduce preprocessor branching
Sigbjørn Skjæret