sync(master): absorb 544 upstream commits — per-arch refactor + Gemma4 12B#59
Merged
Conversation
* vulkan: optimize operations in the IM2COL shader * Add comments and improve the code formatting
…refactor (ggml-org#23345) * mtmd : deepseek-ocr fixes, improvements and refactoring - image processing changes to achieve full parity with Pillow (reference impl) - SAM mask casting only when flash-attn is on - SAM refactor (build_sam() extracted so deepseek-ocr-2 can reuse it) - llama-chat changes to fix server/WebUI issue (new media_markers_first()) - adapted test-chat-template and added test cases for deepseek-ocr - changed regression test for deepseek-ocr to use CER+chrF scores for ground-truth comparison; removed embedding-model - ty.toml ignore unresolved-import for tools/mtmd/tests/** * image-text reordering fix removed * refactor bool add_padding + pad_rounding enum into a single pad_style enum
…3386) ggml_backend_dev_by_name always appends a nullptr sentinel to the devices vector. Skipping nullptr entries prevents assertion failure in ggml_backend_dev_name. Assisted-by: llama.cpp:local pi
* opencl: refactor initialization * opencl: refactor GPU identification * opencl: rename for consistency * opencl: cache global mem size in dev_ctx * opencl: adjust log level * opencl: load argsort and flash_attn kernels in supports_op * argsort kernel must be built for supports_op for querying the max workgroups * flash_attn kernel has many variants, only load them when needed
* Move to backend sampling for MTP draft path Run top_k(10) on the draft backend. D2H transfers happen only for the top 10 logits Make backend sampling more robust and fallback to CPU on failure cases, such as with "-sm tensor" or when a backend doesn't support TOP_K. * Allow sampler chains to be partially offloaded to backend * Add --spec-draft-backend-sampling argument. Enabled by default.
* webui: Add max image size option * remove magic numbers * support all image formats * use const * Move regex to match b64 images to constants * use SETTINGS_KEYS to get max image resolution setting * Do not touch the image if already under the size threshold
…ision (ggml-org#23329) - HunyuanOCR shares the same HF arch and vision layout as HunyuanVL butwas split into a separate path that skipped the +0.1 bilinear sampler used by the HF reference. - Collapse OCR into the HUNYUANVL projector + HUNYUAN_VL text arch
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
* hexagon: remove gathers and better handling of vtcm in ssm-conv * hexagon: relax ssm-conv gating requirements * hexagon: add new prefill ssm-conv backend test * hexagon: remove trailing white space * hex-rope: uninline rope_cache_init, otherwise it breaks after rebaseing with SSM_CONV changes --------- Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
…r SWA-only models (ggml-org#23131) When a model has zero non-SWA attention layers (e.g. a SWA-only slice of Gemma 4), the base KV cache has no layer tensors. The input tensors (self_k_idxs, self_v_idxs, self_kq_mask) are created as graph input nodes but never consumed by any compute node, so the backend scheduler never allocates a buffer for them. Calling mctx->get_base()->set_input_k_idxs() on an unallocated tensor then hits GGML_ASSERT(buffer) at ggml-backend.cpp:194. The same scenario applies symmetrically: if a model had zero SWA layers, the SWA tensors would be unallocated. Fix: guard both the base and SWA set_input calls with null/buffer checks, matching the pattern already used by llm_graph_input_mem_hybrid_iswa::set_input (line ~674) which has the comment: 'base tensors may not be allocated if there are no non-SWA attention layers'. Also fix can_reuse() in the same class to skip the ne[0] and kq_mask checks for unallocated tensors, preventing a null-dereference on the reuse path.
…gml-org#23306) Probably no backends implement only one of 2d get/set, but this might be annoying for some future backend developer trying to add 2d get/set.
* refactor: Improve Git Hooks for UI development * fix: Address review comments * fix: Use absolute git path for `/hooks` Co-authored-by: Pascal <admin@serveurperso.com> --------- Co-authored-by: Pascal <admin@serveurperso.com>
* vocab : add Carbon-3B (HybridDNATokenizer) support
Adds a new BPE pre-type LLAMA_VOCAB_PRE_TYPE_CARBON for the
HybridDNATokenizer used by HuggingFaceBio/Carbon-{500M,3B,8B}.
The base BPE is Qwen3-4B-Base's; what differs is that text inside
<dna>...</dna> regions is chunked into fixed 6-mers (right-padded
with 'A' on the trailing partial), and any base outside ACGT maps
to <oov>.
* src/llama-vocab.{h,cpp}: new pre-type, dispatched from
llm_tokenizer_bpe_session::tokenize.
* src/llama-vocab-carbon.h: pure helpers (tokenize_carbon,
emit_dna_kmers) factored out for unit testing — no llama_vocab
dependency, vocab access goes through a std::function.
* conversion/base.py: detect HybridDNATokenizer by class name in
get_vocab_base_pre (chktxt collides with Qwen3 base since it
has no <dna>), and pass trust_remote_code=True in get_vocab_base
so the custom tokenizer class can load.
* tests/test-tokenizer-carbon.cpp: 12 cases covering single 6-mer,
multi 6-mer, lowercase, invalid base -> <oov>, partial k-mer
right-pad, mixed text+DNA, empty <dna></dna>, unterminated <dna>,
two regions, vocab miss.
* vocab : align Carbon-3B changes with llama.cpp conventions
* Fold tokenize_carbon + emit_dna_kmers inline into
llm_tokenizer_bpe_session (drop src/llama-vocab-carbon.h),
matching how every other tokenizer keeps its helpers inside
llama-vocab.cpp.
* Replace the standalone unit test with the conventional
test-tokenizer-0 row backed by models/ggml-vocab-carbon.gguf
(vocab-only conversion) + .inp/.out fixtures covering single
6-mer, multi 6-mer, lowercase, invalid base -> <oov>, partial
right-pad, mixed text+DNA, empty <dna></dna>, unterminated <dna>,
two regions.
* Register "carbon" in convert_hf_to_gguf_update.py's model list
(pointing at HuggingFaceBio/Carbon-3B) and teach both
AutoTokenizer call sites in the updater to pass
trust_remote_code=True for it, matching how t5 is special-cased.
* vocab : move Carbon dispatch to _set_vocab_carbon + LlamaModel branch
Refactor the conversion-side changes to follow the per-tokenizer-family
convention used by _set_vocab_qwen, _set_vocab_interns1, _set_vocab_glm,
etc. instead of conditionalising the shared get_vocab_base /
get_vocab_base_pre paths.
* conversion/base.py: add _set_vocab_carbon — self-contained, loads
with trust_remote_code=True so HybridDNATokenizer's merged Qwen3 + DNA
vocab is visible, writes tokenizer.ggml.pre = "carbon" directly.
* conversion/llama.py: branch in LlamaModel.set_vocab on
tokenizer_config.json["tokenizer_class"] == "HybridDNATokenizer" and
dispatch to _set_vocab_carbon. Same precedent as conversion/bert.py
(tokenizer_class branch between BertTokenizer / RobertaTokenizer) and
conversion/phi.py.
* conversion/base.py: revert the conditional in get_vocab_base and the
class-name short-circuit in the auto-generated get_vocab_base_pre.
* tests : expand ggml-vocab-carbon.gguf fixtures with model-card examples
Add 6 cases from the Carbon-3B model card on top of the existing edge
coverage: the unterminated basic-completion prompt, the closed 33-bp
example, the metadata-conditioned prompt (with <vertebrate_mammalian>
and <protein_coding_region> which BPE-decompose since they are not in
the vocab), the documented anti-pattern of raw DNA without <dna> tags,
and the two likelihood-scoring examples. Brings the suite to 19 cases.
* vocab : promote HybridDNATokenizer to its own LLAMA_VOCAB_TYPE
Refactor per upstream review:
> This should be its own tokenizer model, ie. carbonhybriddna instead
> of gpt2 and not carbon pre-tokenizer. That way you can keep the
> correct pre-tokenizer, in case that ever changes.
Previously the tokenizer was modelled as LLAMA_VOCAB_TYPE_BPE plus a
new LLAMA_VOCAB_PRE_TYPE_CARBON, which (a) put a CARBON-specific
branch inside llm_tokenizer_bpe_session::tokenize (only existing
pre-types differ in regex, not dispatch logic), and (b) conflated
"hybrid DNA tokenization" with "Qwen3 BPE pre-tokenizer".
This change moves it to its own vocab type, peer to PLAMO2, with the
GGUF model name matching the HF tokenizer class (HybridDNATokenizer):
* include/llama.h: new LLAMA_VOCAB_TYPE_HYBRIDDNA = 7.
* src/llama-vocab.cpp: new llm_tokenizer_hybriddna + session that
owns std::unique_ptr<llm_tokenizer_bpe> for non-<dna> text and
routes raw text through a DNA-aware splitter; wired into
init_tokenizer, tokenize, type_name, byte_to_token, and the
BPE-style token_to_piece case (DNA k-mers + <dna>/</dna>/<oov>
are pure ASCII, so byte-level BPE decoding handles them).
LLAMA_VOCAB_TYPE_HYBRIDDNA gets its own branch in the vocab-type
config block alongside SPM/WPM/UGM/RWKV, where pre_type is set
to QWEN2 and the matching add_space_prefix / escape_whitespaces /
clean_spaces flags are applied — mirroring qwen2's BPE path so
byte-level BPE merging stays bit-identical to the Python
reference for non-DNA text.
* src/llama-vocab.h: drop the short-lived LLAMA_VOCAB_PRE_TYPE_CARBON.
* conversion/base.py: _set_vocab_hybriddna writes
tokenizer.ggml.model = "hybriddna" (no separate pre).
* conversion/llama.py: dispatch on tokenizer_class ==
"HybridDNATokenizer" same as bert.py / phi.py do.
* models/ggml-vocab-hybriddna.gguf{,.inp,.out}: renamed fixture +
regenerated metadata.
* convert_hf_to_gguf_update.py: drop the stale chkhsh entry and
trust_remote_code special-case (no longer needed since dispatch
is now class-name driven, not chkhsh).
Verified end-to-end against HuggingFaceBio/Carbon-{500M,3B,8B}:
tokenization is bit-identical to the Python HybridDNATokenizer for
all 19 test fixtures plus the model-card metadata-conditioned
prompt; greedy completion produces the same DNA continuation as
the Python reference; spec-dec with 500M as draft for 8B still
works.
* vocab : relax llm_tokenizer_bpe assert to allow HYBRIDDNA
* vocab : drop llm_tokenizer_bpe vocab-type assert
* vocab : write tokenizer.ggml.pre for HYBRIDDNA, share BPE dispatch
* vocab : assert BPE or HYBRIDDNA in llm_tokenizer_bpe
* vocab : annotate #endif with PRETOKENIZERDEBUG
* vocab : drop local hybriddna fixture (moves to ggml-org/vocabs)
* deduplicate
* simplify
* simplify
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
when doing a follow-up decode for the draft model, we were always doing the logit computation even though it is not required.
…23459) * app : add batched-bench, fit-params, quantize & perplexity Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add missing main.cpp Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add EOL Signed-off-by: Adrien Gallouët <angt@huggingface.co> --------- Signed-off-by: Adrien Gallouët <angt@huggingface.co>
…#23461) The destroy() function in server_context_impl only cleaned up the main model and context (via llama_init.reset()) but did not free the speculative decoder (spec), draft context (ctx_dft), or draft model (model_dft). For MTP (Multi-Token Prediction) models, ctx_dft holds GPU-allocated resources (KV cache, compute buffers) that are not freed when entering the sleeping state. On each sleep/resume cycle, new resources are allocated without the old ones being freed, leading to a VRAM leak that eventually crashes the server with out-of-memory errors. Fix by explicitly resetting spec, ctx_dft, and model_dft in destroy() before resetting llama_init, ensuring proper cleanup order to avoid use-after-free. ref: ggml-org#23395 Assisted-by: llama.cpp:local pi
…3411) * metal : fix GGML_OP_SET kernel threads * tests : extend test_cpy to support different src/dst shapes Extend test_cpy to support different source and destination tensor shapes for CPY operations (reshaping), where the total number of elements must match. - Renamed ne -> ne_src, added ne_dst parameter (default: use src shape) - Added 50 new reshaping test cases covering 1D<->2D<->3D<->4D conversions - Tests exercise 1024 boundary, small shapes, and large dimensionality changes - Fixed dangling reference bug (storing & to temporary std::array) - Updated all existing test calls with permute/transpose args for compatibility Assisted-by: llama.cpp:local pi * metal : optimize concat kernel with row batching for small widths When ne0 < 256, batch multiple rows into a single threadgroup to improve occupancy. This avoids underutilizing the GPU when processing narrow tensors. - Dispatch nth = min(256, ne0) threads per group - Calculate nrptg (rows per threadgroup) to fill up to 256 threads - Update kernel index calculation to handle the row batching - Add boundary check for i1 >= ne1 Assisted-by: llama.cpp:local pi * tests : clean-up * tests : refactor CPY shape tests to use dimension permutations Replace 75 hardcoded test cases with a loop over permutations of {3, 5, 7, 32} (total elements: 3360). Each src permutation is tested against canonical sorted and reverse dst, skipping identical shapes. Covers F32, F16, and Q4_0 (when both src and dst ne0 == 32). Assisted-by: llama.cpp:local pi
Add n_prompt_tokens, n_prompt_tokens_processed, and n_prompt_tokens_cache to the /slots JSON response. These fields are already tracked internally but were not exposed, making it impossible for clients to monitor prompt evaluation progress during processing.
* tests : move save-load-state from examples to tests - Move examples/save-load-state/ to tests/test-save-load-state.cpp - Remove subdirectory reference from examples/CMakeLists.txt - Add test to tests/CMakeLists.txt as a model test - Remove CODEOWNERS entry for removed example directory Assisted-by: llama.cpp:local pi * cont : update ci
* vulkan: fuse snake activation (mul, sin, sqr, mul, add) Add snake.comp shader with F32 / F16 / BF16 pipelines and ggml_vk_snake_dispatch_fused. The matcher recognizes the naive 5 op decomposition emitted by audio decoders (BigVGAN, Vocos) for snake activation y = x + sin(a*x)^2 * inv_b and rewrites it to a single elementwise kernel. test_snake_fuse from the CUDA PR now also compares CPU naive vs Vulkan fused across F32 / F16 / BF16. * vulkan: address jeffbolznv review for fused snake activation Rename T / C to ne0 / ne1 in the shader and push constants to match the standard naming convention used across the Vulkan backend. Tighten ggml_vk_can_fuse_snake: require x and dst to be contiguous (the shader uses idx = i0 + i1 * ne0) and require a / inv_b to be tightly packed on the broadcast dim (the shader reads data_a[i1]). * vulkan: tighten snake fusion type checks for all operands (address jeffbolznv review) * vulkan: reject snake fusion when ne[2] or ne[3] > 1 (address jeffbolznv review) * vulkan: address 0cc4m review for fused snake activation snake.comp is renamed to follow the ggml DATA_A_* / A_TYPE convention. A_TYPE now applies to the activation tensor data_a instead of the broadcast multiplier, and the bindings become data_a (A_TYPE), data_b (float), data_c (float) and data_d (D_TYPE). A header at the top of the shader maps each buffer to its role in y = x + sin(b * x)^2 * c. On the C++ side, ggml_vk_can_fuse_snake reuses the existing snake_pattern constant instead of duplicating the op list, sin_node is extracted as a named local alongside the other chain nodes, and the broadcast operands a and inv_b are now required to be GGML_TYPE_F32 to match the hardcoded float bindings on data_b and data_c (the previous a->type == x->type would silently reject any future BF16 or F16 chain once the supports_op gate for SIN / SQR is lifted). ggml_vk_snake_dispatch_fused gets an explicit GGML_TYPE_F32 case and GGML_ABORT on default in place of the silent f32 fallback, and a stale comment about data_a[i1] / data_inv_b[i1] is refreshed to match the new binding names.
…default (ggml-org#23462) * cmake : remove STATIC from impl libraries, allow BUILD_SHARED_LIBS control Remove explicit STATIC from all -impl libraries (server, cli, completion, bench, batched-bench, fit-params, quantize, perplexity) so BUILD_SHARED_LIBS controls shared vs static linkage. Add WINDOWS_EXPORT_ALL_SYMBOLS ON for proper DLL export on Windows. Assisted-by: llama.cpp:local pi * cmake : enable LLAMA_BUILD_APP by default Assisted-by: llama.cpp:local pi * ci : disable app in build-cmake-pkg.yml
…#23511) * pi : update * ci : fix ios build * ci : fix andoroid * ci : fix apple builds * cmake : add install() for impl libraries Add install(TARGETS <target> LIBRARY) for all -impl libraries that were changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in commit bb28c1f. Without this, cmake --install fails to copy the shared libraries, causing runtime errors like: llama-server: error while loading shared libraries: libllama-server-impl.so Ref: ggml-org#23494 (comment) Assisted-by: llama.cpp:local pi * ci : fix xcframework build
* vocab : mark hybriddna k-mers to avoid BPE token collisions * improved loop --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
* ggml-zendnn : add Q8_0 quantization support * ggml-zendnn : sync with latest ZenDNN * ggml-zendnn : address review comments for Q8_0
* model: support for Mellum architecture * model: improve mellum.py formatting * model: improve mellum.py formatting once again * deps: downgrade transformers to 4.57.6 (to fix CI) * deps: remove huggingface_hub dependency * deps: remove huggingface_hub from test requirements --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* hex-ops: fix profiler output (ie remove the redundant NONEs) * hex-prof: update profiling script to support tot.usec column
* tests : add support for qwen3 SSM archs * arch : add LLM_KV_ATTENTION_RECURRENT_LAYERS * cont : naming + TODOs
* cuda: reserve space for quantize kv-cache at startup * address review comments * remove forward decl Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * remove assert in ggml-cuda.cu Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
…gml-org#24030) * Removes __restrict__ from PDL kernel headers due to incompatibility with PDL. Adds preprocessor directives based on arch in kernel body to add __restrict__ to retain performance on older architectures. * Simplifies new __restrict__ usage via macro * Add hopper to PDL __restrict__ fix. Co-authored-by: Oliver Simons <osimons@nvidia.com> --------- Co-authored-by: Oliver Simons <osimons@nvidia.com>
* add model * nits
* qwen35: use post-norm hidden state for MTP * rename pre_norm to nextn * fix step35
* Tidy up SYCL doc a bit - Add explicit links to referenced items - Fix spelling errors Signed-off-by: Todd Malsbary <todd.malsbary@intel.com> * Correct documented default for GGML_SYCL_GRAPH The default is ON, not OFF: $ cmake -LAH -B build | grep GGML_SYCL_GRAPH ... GGML_SYCL_GRAPH:BOOL=ON Signed-off-by: Todd Malsbary <todd.malsbary@intel.com> * Move docker instructions from SYCL.md to docker.md This makes them directly accesible from the Quick Start section of the top-level README.md. Signed-off-by: Todd Malsbary <todd.malsbary@intel.com> * Refer to intel.Dockerfile for ARGs and their defaults The defaults are always changing; this avoids accuracy errors from duplicating the information. Signed-off-by: Todd Malsbary <todd.malsbary@intel.com> * Remove mention of Nvidia in SYCL row of backend table This support was removed in 2026.02 - refer to the SYCL.md News. Signed-off-by: Todd Malsbary <todd.malsbary@intel.com> --------- Signed-off-by: Todd Malsbary <todd.malsbary@intel.com>
…2754) * ggml-cpu: add rvv 512b,1024b impls for iq4_xs * ggml-cpu: refactor; add rvv 512b, 1024b impls for q6_K, i-quants * ggml-cpu: refactor; add 512 and 1024 implementations of tq3_s, iq3_xxs, iq2_s, iq2_xs, iq2_xxs improve iq2_xs impl for rvv 256 Co-authored-by: Rehan Qasim <rehan.qasim@10xengineers.ai> --------- Co-authored-by: taimur-10x <taimur.ahmad@10xengineers.ai> Co-authored-by: Rehan Qasim <rehan.qasim@10xengineers.ai>
…rt (ggml-org#23834) * Start work on flash_attn refactor * Refactor * Split k/v quantization * Refactor and abstract quantization logic for flash_attn and mul_mat * Add quantization support to tile path * formatting * Move to functions, add a check
…#24073) * tests : refactor test-save-load-state to accept token input - Default prompt is now empty; when not provided, generate n_batch random tokens (useful for models without a tokenizer) - Tokenization happens once upfront; pass token vector to test functions - generate_tokens prints token IDs instead of decoded pieces - Use llama_model_get_vocab / llama_vocab_n_tokens API - Upgrade log level from LOG_TRC to LOG_INF for visibility Assisted-by: llama.cpp:local pi * cont : use llama_tokens alias
# Conflicts: # .github/workflows/ui.yml # .gitignore # convert_hf_to_gguf.py # ggml/src/ggml-cpu/arch-fallback.h # tests/test-backend-ops.cpp # tools/cli/README.md # tools/completion/README.md # tools/server/README-dev.md # tools/server/README.md # tools/server/public/bundle.css # tools/server/public/bundle.js # tools/server/public/index.html # tools/server/server-chat.cpp # tools/server/server-models.cpp # tools/ui/.gitignore # tools/ui/.npmrc # tools/ui/.prettierignore # tools/ui/.prettierrc # tools/ui/.storybook/decorators/ModeWatcherDecorator.svelte # tools/ui/.storybook/decorators/TooltipProviderDecorator.svelte # tools/ui/.storybook/main.ts # tools/ui/.storybook/preview.ts # tools/ui/.storybook/vitest.setup.ts # tools/ui/README.md # tools/ui/components.json # tools/ui/docs/architecture/high-level-architecture-simplified.md # tools/ui/docs/architecture/high-level-architecture.md # tools/ui/docs/flows/chat-flow.md # tools/ui/docs/flows/conversations-flow.md # tools/ui/docs/flows/data-flow-simplified-model-mode.md # tools/ui/docs/flows/data-flow-simplified-router-mode.md # tools/ui/docs/flows/database-flow.md # tools/ui/docs/flows/mcp-flow.md # tools/ui/docs/flows/models-flow.md # tools/ui/docs/flows/server-flow.md # tools/ui/docs/flows/settings-flow.md # tools/ui/eslint.config.js # tools/ui/package-lock.json # tools/ui/package.json # tools/ui/playwright.config.ts # tools/ui/scripts/dev.sh # tools/ui/scripts/vite-plugin-llama-cpp-build.ts # tools/ui/src/app.css # tools/ui/src/app.d.ts # tools/ui/src/app.html # tools/ui/src/lib/actions/fade-in-view.svelte.ts # tools/ui/src/lib/components/app/badges/BadgeInfo.svelte # tools/ui/src/lib/components/app/badges/index.ts # tools/ui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentsList/ChatAttachmentsListItem/ChatAttachmentsListItemMcpPrompt.svelte # tools/ui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentsList/ChatAttachmentsListItem/ChatAttachmentsListItemMcpResource.svelte # tools/ui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentsList/ChatAttachmentsListItem/ChatAttachmentsListItemThumbnailImage.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatForm.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormActions/ChatFormActionRecord.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormActions/ChatFormActionSubmit.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormFileInputInvisible.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormMcpResourcesList.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPicker/ChatFormPickerItemHeader.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPicker/ChatFormPickerList.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPicker/ChatFormPickerListItem.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPicker/ChatFormPickerListItemSkeleton.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPicker/ChatFormPickerPopover.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPickerMcpPrompts/ChatFormPickerMcpPrompts.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPickerMcpPrompts/ChatFormPromptPickerArgumentForm.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPickerMcpPrompts/ChatFormPromptPickerArgumentInput.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormPickers/ChatFormPickerMcpResources.svelte # tools/ui/src/lib/components/app/chat/ChatForm/ChatFormTextarea.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessage.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageAssistant/ChatMessageAssistant.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageMcpPrompt/ChatMessageMcpPrompt.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageMcpPrompt/ChatMessageMcpPromptContent.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageSystem/ChatMessageSystem.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageActions/ChatMessageActionIcons/ChatMessageActionIcons.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageAgenticContent.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageEditForm.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageStatistics/ChatMessageStatistics.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageStatistics/ChatMessageStatisticsBadge.svelte # tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessages.svelte # tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreen.svelte # tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreenDragOverlay.svelte # tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreenForm.svelte # tools/ui/src/lib/components/app/chat/ChatScreen/ChatScreenProcessingInfo.svelte # tools/ui/src/lib/components/app/chat/index.ts # tools/ui/src/lib/components/app/content/CollapsibleContentBlock.svelte # tools/ui/src/lib/components/app/content/MarkdownContent/MarkdownContent.svelte # tools/ui/src/lib/components/app/content/MarkdownContent/plugins/rehype/enhance-links.ts # tools/ui/src/lib/components/app/content/MarkdownContent/plugins/rehype/rehype-rtl-support.ts # tools/ui/src/lib/components/app/content/MarkdownContent/plugins/rehype/resolve-attachment-images.ts # tools/ui/src/lib/components/app/content/MarkdownContent/plugins/rehype/table-html-restorer.ts # tools/ui/src/lib/components/app/content/MarkdownContent/plugins/remark/literal-html.ts # tools/ui/src/lib/components/app/content/SyntaxHighlightedCode.svelte # tools/ui/src/lib/components/app/content/index.ts # tools/ui/src/lib/components/app/dialogs/DialogChatError.svelte # tools/ui/src/lib/components/app/dialogs/DialogCodePreview.svelte # tools/ui/src/lib/components/app/dialogs/DialogConfirmation.svelte # tools/ui/src/lib/components/app/dialogs/DialogConversationSelection.svelte # tools/ui/src/lib/components/app/dialogs/DialogConversationTitleUpdate.svelte # tools/ui/src/lib/components/app/dialogs/DialogEmptyFileAlert.svelte # tools/ui/src/lib/components/app/dialogs/DialogMcpResourcePreview.svelte # tools/ui/src/lib/components/app/dialogs/DialogMcpResourcesBrowser.svelte # tools/ui/src/lib/components/app/dialogs/DialogModelInformation.svelte # tools/ui/src/lib/components/app/dialogs/DialogModelNotAvailable.svelte # tools/ui/src/lib/components/app/dialogs/index.ts # tools/ui/src/lib/components/app/forms/InputWithSuggestions.svelte # tools/ui/src/lib/components/app/forms/KeyValuePairs.svelte # tools/ui/src/lib/components/app/forms/SearchInput.svelte # tools/ui/src/lib/components/app/forms/index.ts # tools/ui/src/lib/components/app/index.ts # tools/ui/src/lib/components/app/mcp/McpCapabilitiesBadges.svelte # tools/ui/src/lib/components/app/mcp/McpConnectionLogs.svelte # tools/ui/src/lib/components/app/mcp/McpLogo.svelte # tools/ui/src/lib/components/app/mcp/McpResourcePreview.svelte # tools/ui/src/lib/components/app/mcp/McpResourceTemplateForm.svelte # tools/ui/src/lib/components/app/mcp/McpResourcesBrowser/McpResourcesBrowser.svelte # tools/ui/src/lib/components/app/mcp/McpResourcesBrowser/McpResourcesBrowserEmptyState.svelte # tools/ui/src/lib/components/app/mcp/McpResourcesBrowser/McpResourcesBrowserHeader.svelte # tools/ui/src/lib/components/app/mcp/McpResourcesBrowser/McpResourcesBrowserServerItem.svelte # tools/ui/src/lib/components/app/mcp/McpResourcesBrowser/mcp-resources-browser.ts # tools/ui/src/lib/components/app/mcp/McpServerCard/McpServerCard.svelte # tools/ui/src/lib/components/app/mcp/McpServerCard/McpServerCardActions.svelte # tools/ui/src/lib/components/app/mcp/McpServerCard/McpServerCardDeleteDialog.svelte # tools/ui/src/lib/components/app/mcp/McpServerCard/McpServerCardEditForm.svelte # tools/ui/src/lib/components/app/mcp/McpServerCard/McpServerCardHeader.svelte # tools/ui/src/lib/components/app/mcp/McpServerCard/McpServerCardToolsList.svelte # tools/ui/src/lib/components/app/mcp/McpServerCardSkeleton.svelte # tools/ui/src/lib/components/app/mcp/McpServerForm.svelte # tools/ui/src/lib/components/app/mcp/McpServerInfo.svelte # tools/ui/src/lib/components/app/mcp/index.ts # tools/ui/src/lib/components/app/misc/ConversationSelection.svelte # tools/ui/src/lib/components/app/misc/HorizontalScrollCarousel.svelte # tools/ui/src/lib/components/app/misc/KeyboardShortcutInfo.svelte # tools/ui/src/lib/components/app/misc/TruncatedText.svelte # tools/ui/src/lib/components/app/misc/index.ts # tools/ui/src/lib/components/app/models/ModelBadge.svelte # tools/ui/src/lib/components/app/models/ModelId.svelte # tools/ui/src/lib/components/app/models/ModelsSelectorList.svelte # tools/ui/src/lib/components/app/models/ModelsSelectorOption.svelte # tools/ui/src/lib/components/app/models/index.ts # tools/ui/src/lib/components/app/models/utils.ts # tools/ui/src/lib/components/app/navigation/DropdownMenuActions.svelte # tools/ui/src/lib/components/app/navigation/DropdownMenuSearchable.svelte # tools/ui/src/lib/components/app/navigation/SidebarNavigation/SidebarNavigation.svelte # tools/ui/src/lib/components/app/navigation/SidebarNavigation/SidebarNavigationConversationItem.svelte # tools/ui/src/lib/components/app/navigation/SidebarNavigation/SidebarNavigationSearch.svelte # tools/ui/src/lib/components/app/server/ServerErrorSplash.svelte # tools/ui/src/lib/components/app/server/ServerLoadingSplash.svelte # tools/ui/src/lib/components/app/server/ServerStatus.svelte # tools/ui/src/lib/components/app/server/index.ts # tools/ui/src/lib/components/app/settings/SettingsChat/SettingsChatFields.svelte # tools/ui/src/lib/components/app/settings/SettingsChat/SettingsChatImportExportTab.svelte # tools/ui/src/lib/components/app/settings/SettingsChat/SettingsChatParameterSourceIndicator.svelte # tools/ui/src/lib/components/app/settings/SettingsFooter.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-action.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-cancel.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-content.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-description.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-footer.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-header.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-overlay.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-title.svelte # tools/ui/src/lib/components/ui/alert-dialog/alert-dialog-trigger.svelte # tools/ui/src/lib/components/ui/alert-dialog/index.ts # tools/ui/src/lib/components/ui/alert/alert-description.svelte # tools/ui/src/lib/components/ui/alert/alert-title.svelte # tools/ui/src/lib/components/ui/alert/alert.svelte # tools/ui/src/lib/components/ui/alert/index.ts # tools/ui/src/lib/components/ui/badge/badge.svelte # tools/ui/src/lib/components/ui/badge/index.ts # tools/ui/src/lib/components/ui/button/button.svelte # tools/ui/src/lib/components/ui/button/index.ts # tools/ui/src/lib/components/ui/card/card-action.svelte # tools/ui/src/lib/components/ui/card/card-content.svelte # tools/ui/src/lib/components/ui/card/card-description.svelte # tools/ui/src/lib/components/ui/card/card-footer.svelte # tools/ui/src/lib/components/ui/card/card-header.svelte # tools/ui/src/lib/components/ui/card/card-title.svelte # tools/ui/src/lib/components/ui/card/card.svelte # tools/ui/src/lib/components/ui/card/index.ts # tools/ui/src/lib/components/ui/checkbox/checkbox.svelte # tools/ui/src/lib/components/ui/checkbox/index.ts # tools/ui/src/lib/components/ui/collapsible/collapsible-content.svelte # tools/ui/src/lib/components/ui/collapsible/collapsible-trigger.svelte # tools/ui/src/lib/components/ui/collapsible/collapsible.svelte # tools/ui/src/lib/components/ui/collapsible/index.ts # tools/ui/src/lib/components/ui/dialog/dialog-close.svelte # tools/ui/src/lib/components/ui/dialog/dialog-content.svelte # tools/ui/src/lib/components/ui/dialog/dialog-description.svelte # tools/ui/src/lib/components/ui/dialog/dialog-footer.svelte # tools/ui/src/lib/components/ui/dialog/dialog-header.svelte # tools/ui/src/lib/components/ui/dialog/dialog-overlay.svelte # tools/ui/src/lib/components/ui/dialog/dialog-title.svelte # tools/ui/src/lib/components/ui/dialog/dialog-trigger.svelte # tools/ui/src/lib/components/ui/dialog/index.ts # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-checkbox-item.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-content.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-group-heading.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-group.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-item.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-label.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-radio-group.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-radio-item.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-separator.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-shortcut.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-sub-trigger.svelte # tools/ui/src/lib/components/ui/dropdown-menu/dropdown-menu-trigger.svelte # tools/ui/src/lib/components/ui/dropdown-menu/index.ts # tools/ui/src/lib/components/ui/input/index.ts # tools/ui/src/lib/components/ui/input/input.svelte # tools/ui/src/lib/components/ui/label/index.ts # tools/ui/src/lib/components/ui/label/label.svelte # tools/ui/src/lib/components/ui/popover/index.ts # tools/ui/src/lib/components/ui/popover/popover-close.svelte # tools/ui/src/lib/components/ui/popover/popover-content.svelte # tools/ui/src/lib/components/ui/popover/popover-portal.svelte # tools/ui/src/lib/components/ui/popover/popover-trigger.svelte # tools/ui/src/lib/components/ui/popover/popover.svelte # tools/ui/src/lib/components/ui/scroll-area/index.ts # tools/ui/src/lib/components/ui/scroll-area/scroll-area-scrollbar.svelte # tools/ui/src/lib/components/ui/scroll-area/scroll-area.svelte # tools/ui/src/lib/components/ui/select/index.ts # tools/ui/src/lib/components/ui/select/select-content.svelte # tools/ui/src/lib/components/ui/select/select-group-heading.svelte # tools/ui/src/lib/components/ui/select/select-group.svelte # tools/ui/src/lib/components/ui/select/select-item.svelte # tools/ui/src/lib/components/ui/select/select-label.svelte # tools/ui/src/lib/components/ui/select/select-scroll-down-button.svelte # tools/ui/src/lib/components/ui/select/select-scroll-up-button.svelte # tools/ui/src/lib/components/ui/select/select-separator.svelte # tools/ui/src/lib/components/ui/select/select-trigger.svelte # tools/ui/src/lib/components/ui/separator/index.ts # tools/ui/src/lib/components/ui/separator/separator.svelte # tools/ui/src/lib/components/ui/sheet/index.ts # tools/ui/src/lib/components/ui/sheet/sheet-close.svelte # tools/ui/src/lib/components/ui/sheet/sheet-content.svelte # tools/ui/src/lib/components/ui/sheet/sheet-description.svelte # tools/ui/src/lib/components/ui/sheet/sheet-footer.svelte # tools/ui/src/lib/components/ui/sheet/sheet-header.svelte # tools/ui/src/lib/components/ui/sheet/sheet-overlay.svelte # tools/ui/src/lib/components/ui/sheet/sheet-title.svelte # tools/ui/src/lib/components/ui/sheet/sheet-trigger.svelte # tools/ui/src/lib/components/ui/sidebar/constants.ts # tools/ui/src/lib/components/ui/sidebar/context.svelte.ts # tools/ui/src/lib/components/ui/sidebar/index.ts # tools/ui/src/lib/components/ui/sidebar/sidebar-content.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-footer.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-group-action.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-group-content.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-group-label.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-group.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-header.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-input.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-inset.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-action.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-badge.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-button.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-item.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-skeleton.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-sub-button.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-sub-item.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu-sub.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-menu.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-provider.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-rail.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-separator.svelte # tools/ui/src/lib/components/ui/sidebar/sidebar-trigger.svelte # tools/ui/src/lib/components/ui/skeleton/index.ts # tools/ui/src/lib/components/ui/skeleton/skeleton.svelte # tools/ui/src/lib/components/ui/switch/index.ts # tools/ui/src/lib/components/ui/switch/switch.svelte # tools/ui/src/lib/components/ui/table/index.ts # tools/ui/src/lib/components/ui/table/table-body.svelte # tools/ui/src/lib/components/ui/table/table-caption.svelte # tools/ui/src/lib/components/ui/table/table-cell.svelte # tools/ui/src/lib/components/ui/table/table-footer.svelte # tools/ui/src/lib/components/ui/table/table-head.svelte # tools/ui/src/lib/components/ui/table/table-header.svelte # tools/ui/src/lib/components/ui/table/table-row.svelte # tools/ui/src/lib/components/ui/table/table.svelte # tools/ui/src/lib/components/ui/textarea/index.ts # tools/ui/src/lib/components/ui/textarea/textarea.svelte # tools/ui/src/lib/components/ui/tooltip/index.ts # tools/ui/src/lib/components/ui/tooltip/tooltip-content.svelte # tools/ui/src/lib/components/ui/tooltip/tooltip-trigger.svelte # tools/ui/src/lib/components/ui/utils.ts # tools/ui/src/lib/constants/agentic.ts # tools/ui/src/lib/constants/attachment-labels.ts # tools/ui/src/lib/constants/auto-scroll.ts # tools/ui/src/lib/constants/binary-detection.ts # tools/ui/src/lib/constants/cache.ts # tools/ui/src/lib/constants/chat-form.ts # tools/ui/src/lib/constants/code-blocks.ts # tools/ui/src/lib/constants/code.ts # tools/ui/src/lib/constants/css-classes.ts # tools/ui/src/lib/constants/floating-ui-constraints.ts # tools/ui/src/lib/constants/formatters.ts # tools/ui/src/lib/constants/index.ts # tools/ui/src/lib/constants/key-value-pairs.ts # tools/ui/src/lib/constants/latex-protection.ts # tools/ui/src/lib/constants/literal-html.ts # tools/ui/src/lib/constants/markdown.ts # tools/ui/src/lib/constants/max-bundle-size.ts # tools/ui/src/lib/constants/mcp-form.ts # tools/ui/src/lib/constants/mcp-resource.ts # tools/ui/src/lib/constants/mcp.ts # tools/ui/src/lib/constants/message-export.ts # tools/ui/src/lib/constants/model-id.ts # tools/ui/src/lib/constants/precision.ts # tools/ui/src/lib/constants/processing-info.ts # tools/ui/src/lib/constants/settings-keys.ts # tools/ui/src/lib/constants/supported-file-types.ts # tools/ui/src/lib/constants/table-html-restorer.ts # tools/ui/src/lib/constants/tooltip-config.ts # tools/ui/src/lib/constants/uri-template.ts # tools/ui/src/lib/constants/viewport.ts # tools/ui/src/lib/contexts/chat-actions.context.ts # tools/ui/src/lib/contexts/index.ts # tools/ui/src/lib/contexts/message-edit.context.ts # tools/ui/src/lib/enums/agentic.enums.ts # tools/ui/src/lib/enums/chat.enums.ts # tools/ui/src/lib/enums/files.enums.ts # tools/ui/src/lib/enums/keyboard.enums.ts # tools/ui/src/lib/enums/mcp.enums.ts # tools/ui/src/lib/enums/model.enums.ts # tools/ui/src/lib/enums/server.enums.ts # tools/ui/src/lib/enums/settings.enums.ts # tools/ui/src/lib/enums/ui.enums.ts # tools/ui/src/lib/hooks/use-auto-scroll.svelte.ts # tools/ui/src/lib/hooks/use-processing-state.svelte.ts # tools/ui/src/lib/services/chat.service.ts # tools/ui/src/lib/services/database.service.ts # tools/ui/src/lib/services/index.ts # tools/ui/src/lib/services/mcp.service.ts # tools/ui/src/lib/services/models.service.ts # tools/ui/src/lib/services/parameter-sync.service.spec.ts # tools/ui/src/lib/services/props.service.ts # tools/ui/src/lib/stores/agentic.svelte.ts # tools/ui/src/lib/stores/chat.svelte.ts # tools/ui/src/lib/stores/conversations.svelte.ts # tools/ui/src/lib/stores/mcp-resources.svelte.ts # tools/ui/src/lib/stores/mcp.svelte.ts # tools/ui/src/lib/stores/models.svelte.ts # tools/ui/src/lib/stores/persisted.svelte.ts # tools/ui/src/lib/stores/server.svelte.ts # tools/ui/src/lib/stores/settings.svelte.ts # tools/ui/src/lib/types/agentic.d.ts # tools/ui/src/lib/types/api.d.ts # tools/ui/src/lib/types/chat.d.ts # tools/ui/src/lib/types/common.d.ts # tools/ui/src/lib/types/database.d.ts # tools/ui/src/lib/types/index.ts # tools/ui/src/lib/types/mcp.d.ts # tools/ui/src/lib/types/models.d.ts # tools/ui/src/lib/types/settings.d.ts # tools/ui/src/lib/utils/abort.ts # tools/ui/src/lib/utils/agentic.ts # tools/ui/src/lib/utils/api-fetch.ts # tools/ui/src/lib/utils/api-headers.ts # tools/ui/src/lib/utils/api-key-validation.ts # tools/ui/src/lib/utils/attachment-display.ts # tools/ui/src/lib/utils/attachment-type.ts # tools/ui/src/lib/utils/audio-recording.ts # tools/ui/src/lib/utils/autoresize-textarea.ts # tools/ui/src/lib/utils/branching.ts # tools/ui/src/lib/utils/browser-only.ts # tools/ui/src/lib/utils/cache-ttl.ts # tools/ui/src/lib/utils/clipboard.ts # tools/ui/src/lib/utils/code.ts # tools/ui/src/lib/utils/config-helpers.ts # tools/ui/src/lib/utils/conversation-utils.ts # tools/ui/src/lib/utils/convert-files-to-extra.ts # tools/ui/src/lib/utils/cors-proxy.ts # tools/ui/src/lib/utils/data-url.ts # tools/ui/src/lib/utils/debounce.ts # tools/ui/src/lib/utils/file-preview.ts # tools/ui/src/lib/utils/file-type.ts # tools/ui/src/lib/utils/formatters.ts # tools/ui/src/lib/utils/headers.ts # tools/ui/src/lib/utils/image-error-fallback.ts # tools/ui/src/lib/utils/index.ts # tools/ui/src/lib/utils/is-ime-composing.ts # tools/ui/src/lib/utils/latex-protection.ts # tools/ui/src/lib/utils/legacy-migration.ts # tools/ui/src/lib/utils/mcp.ts # tools/ui/src/lib/utils/modality-file-validation.ts # tools/ui/src/lib/utils/model-names.ts # tools/ui/src/lib/utils/pdf-processing.ts # tools/ui/src/lib/utils/portal-to-body.ts # tools/ui/src/lib/utils/precision.ts # tools/ui/src/lib/utils/process-uploaded-files.ts # tools/ui/src/lib/utils/redact.ts # tools/ui/src/lib/utils/request-helpers.ts # tools/ui/src/lib/utils/sanitize.ts # tools/ui/src/lib/utils/svg-to-png.ts # tools/ui/src/lib/utils/syntax-highlight-language.ts # tools/ui/src/lib/utils/text-files.ts # tools/ui/src/lib/utils/text.ts # tools/ui/src/lib/utils/uri-template.ts # tools/ui/src/lib/utils/uuid.ts # tools/ui/src/lib/utils/webp-to-png.ts # tools/ui/src/routes/(chat)/+page.svelte # tools/ui/src/routes/(chat)/+page.ts # tools/ui/src/routes/(chat)/chat/[id]/+page.svelte # tools/ui/src/routes/(chat)/chat/[id]/+page.ts # tools/ui/src/routes/+error.svelte # tools/ui/src/routes/+layout.svelte # tools/ui/src/styles/katex-custom.scss # tools/ui/static/favicon.svg # tools/ui/static/tts-default-ref.mp3 # tools/ui/svelte.config.js # tools/ui/tests/client/components/TestWrapper.svelte # tools/ui/tests/client/page.svelte.test.ts # tools/ui/tests/stories/ChatMessage.stories.svelte # tools/ui/tests/stories/ChatScreenForm.stories.svelte # tools/ui/tests/stories/Introduction.mdx # tools/ui/tests/stories/MarkdownContent.stories.svelte # tools/ui/tests/stories/SidebarNavigation.stories.svelte # tools/ui/tests/stories/fixtures/ai-tutorial.ts # tools/ui/tests/stories/fixtures/api-docs.ts # tools/ui/tests/stories/fixtures/assets/1.jpg # tools/ui/tests/stories/fixtures/assets/beautiful-flowers-lotus.webp # tools/ui/tests/stories/fixtures/assets/example.pdf # tools/ui/tests/stories/fixtures/assets/hf-logo.svg # tools/ui/tests/stories/fixtures/blog-post.ts # tools/ui/tests/stories/fixtures/data-analysis.ts # tools/ui/tests/stories/fixtures/empty.ts # tools/ui/tests/stories/fixtures/math-formulas.ts # tools/ui/tests/stories/fixtures/readme.ts # tools/ui/tests/stories/fixtures/storybook-mocks.ts # tools/ui/tests/unit/agentic-sections.test.ts # tools/ui/tests/unit/agentic-strip.test.ts # tools/ui/tests/unit/clipboard.test.ts # tools/ui/tests/unit/latex-protection.test.ts # tools/ui/tests/unit/mcp-service.test.ts # tools/ui/tests/unit/model-id-parser.test.ts # tools/ui/tests/unit/model-names.test.ts # tools/ui/tests/unit/reasoning-context.test.ts # tools/ui/tests/unit/redact.test.ts # tools/ui/tests/unit/request-helpers.test.ts # tools/ui/tests/unit/sanitize-headers.test.ts # tools/ui/tests/unit/uri-template.test.ts # tools/ui/tsconfig.json # tools/ui/vite.config.ts
This was referenced Jun 4, 2026
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
Markus asked for ht-on-top-of-master so Gemma 4 12B (`Gemma4ForCausalLM`) is runnable.
That architecture is a text-only variant added upstream in PR #23682 (commit `dbe9c0c8c`) and registered in `conversion/gemma.py:617`. It rides along with the larger per-arch model refactor (commit `994118a18`) that moved `llama_model::build_graph()` out of one monolithic switch and into 132 per-arch classes under `src/models/`.
Before this merge, neither change was on `origin/ht`. After this merge, both are.
What
`origin/ht` + `origin/master` (FF'd to upstream `006640408` earlier today) → merge commit `df61855b7`.
Conflict resolution
Verified
Known follow-ups