UPSTREAM PR #16618: webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI #24
Conversation
…(#16345) * make ggml_vk_default_dispatcher support older vulkan headers * simpilfy with using
* feat: Add a setting to include model name used to generate the message * feat: UI improvements * feat: Save model info along with the database message entry creation * chore: Build webui static output
* feat: Improve code block theming * chore: update webui build output * chore: Update webui static build
…onditional rendering for Actions Dropdown for Chat Conversation Items (#16369) * fix: Render Conversation action dialogs as singletons from Chat Sidebar level * chore: update webui build output * fix: Render Actions Dropdown conditionally only when user hovers conversation item + remove unused markup * chore: Update webui static build * fix: Always truncate conversation names * chore: Update webui static build
* common: introduce http.h for httplib-based client This change moves cpp-httplib based URL parsing and client setup into a new header `common/http.h`, and integrates it in `arg.cpp` and `run.cpp`. It is an iteration towards removing libcurl, while intentionally minimizing changes to existing code to guarantee the same behavior when `LLAMA_CURL` is used. Signed-off-by: Adrien Gallouët <[email protected]> * tools : add missing WIN32_LEAN_AND_MEAN Signed-off-by: Adrien Gallouët <[email protected]> --------- Signed-off-by: Adrien Gallouët <[email protected]> Signed-off-by: Adrien Gallouët <[email protected]>
* CI: Properly install rocwmma for hip builds on windows we now windows install rocwmma from ubuntu pacakges * CI: update linux rocm docker build to use rocm 7.0
…16075) * Fix to use hidden_size_per_head * Fix num heads * Fix array * Fix loading weights * Support old GGUF converted by the previous version of llama.cpp * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * Move shared parameter definitions to the outside of loop * Not calculating n_embd_head_k,v by n_embd / n_head --------- Co-authored-by: Sigbjørn Skjæret <[email protected]>
…0 (#16221) * HIP: Disable ROCWMMA fatt on CDNA when compiled against ROCWMMA 2.0.0 rocwmma 2.0.0 includes a bug in the code fakeing fp16 accumulation on CDNA * CUDA: Fix volta condition in ggml_cuda_should_use_wmma_fattn
* update oneapi to 2025.2, use deep-learning-essentials to replace base-tool * update to 2025.2 use deeplearn essi to replace base toolkit * add missed dll * add deep learning essentials * add sycl-ls --------- Co-authored-by: Zhang Jianyu <[email protected]>
Signed-off-by: Xiaodong Ye <[email protected]>
* First attempt * No permute during convert (fixes qk tensors), proper norm application. * RoPE = NeoX * Coherence! * Migrate xielu params from tensors to hyperparameters * Simple CUDA kernel * Revert stupid LLM refactorings * Chat template support * configchecker / flake8 errors * Reorder unary.cu * I do conclude that LLMs are, in fact, stupid. * Fix after merge * Final newline * Make xIELU an UNARY_OP * Final newline * Correctly account for parameter shift * Argh. * Update ggml/src/ggml-cpu/unary-ops.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Refactor: remove unused methods, inline and factorize softplus, add const modifiers * Revert CUDA changes, implement xIELU as a separate OP * Pesky newline * Add float2half / half2float for F16 inputs/outputs * CUDA variants, attempt 2 * Actually, attempt 3 * Update ggml/src/ggml-cuda/unary.cu Co-authored-by: Johannes Gäßler <[email protected]> * Missing convert header * Proper formula and reference for xIELU in the comments. * Modify unary-ops.cpp to add the functor-based logic besides the template system to retain optimizations * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <[email protected]> * Add tensor mappings for Apertus to global list instead * Fix lazy on scalars * Update ggml/src/ggml-cuda/unary.cu Co-authored-by: Johannes Gäßler <[email protected]> * Add comment about the constraints on positive/negative alpha * Change `softplus` to `ggml_softplus` --------- Co-authored-by: Georgi Gerganov <[email protected]> Co-authored-by: Johannes Gäßler <[email protected]> Co-authored-by: Sigbjørn Skjæret <[email protected]>
* Add inplace softmax * Move rms_norm to split row approach * Update debug for supports_op * clean up debug statements * Update tests/test-backend-ops.cpp Co-authored-by: Georgi Gerganov <[email protected]> --------- Co-authored-by: Georgi Gerganov <[email protected]>
…389) * do not use more threads than physically available * ensure n_threads > 0 Co-authored-by: Jeff Bolz <[email protected]> --------- Co-authored-by: Jeff Bolz <[email protected]>
…rolling (#16356) Use <svelte:window bind:innerHeight> instead of manual resize listener Co-authored-by: Aleksander Grygier <[email protected]>
* fix: Include just the currently active message branches instead of all in chat completions request * chore: Build webui static output * chore: Formatting * chore: update webui build output
…GGML_KQ_MASK_PAD) (#16316)
…quest (#16405) * feat: Capture model name only after first token (streaming) or completed request (non-streaming) * chore: update webui build output * chore: update webui build output
This commit updates the macos-13 runners to macos-15-intel. The motivation for this changes is the macos-13 runners are scheduled to be retired on 2025-12-04. Refs: https://github.blog/changelog/2025-09-19-github-actions-macos-13-runner-image-is-closing-down/
When computing sinks, the cm1 shader was looping r from 0 to Br rather than to rows_per_thread. I must have copied this from the scalar path (where it is correct), and somehow it wasn't causing failures on current drivers.
…6354) * vulkan: Replace uses of maxMemoryAllocationSize and VK_WHOLE_SIZE Replace maxMemoryAllocationSize check with maxBufferSize when creating buffers. The maxMemoryAllocationSize limit is a "soft" limit and allocations can succeed beyond that limit. This allows > 4GB buffers to be allocated on some implementations (e.g. NVIDIA) and tensors this large can be used for im2col and mul_mat. For temporary buffers (prealloc_x/y/etc) check against maxStorageBufferRange. I'm not sure this check is ideal, but we always use these buffers as a single full size binding and the limit may be smaller than maxMemoryAllocationSize or maxBufferSize, so I think this is reasonable. Replace descriptor range uses of VK_WHOLE_SIZE with a manually computed range. The maxStorageBufferRange may be smaller than the maxBufferSize or maxMemoryAllocationSize (and the Vulkan spec warns about this in a note) and it's invalid usage if VK_WHOLE_SIZE computes a range larger than maxStorageBufferRange. With this change, it should be possible to generate videos using wan networks in stable-diffusion.cpp. * vulkan: Add env var GGML_VK_FORCE_MAX_BUFFER_SIZE and use stoull
* fix: resolve message disappearing issue when navigating between regenerated siblings by using current leaf nodes instead of cached sibling IDs * chore: update webui build output * chore: update webui build output
reallocation is needed if a single chunk grows in size, even if total allocation size stays the same or is lower
…ersistence in chat UI - Purely visual and diagnostic change, no effect on model context, prompt construction, or inference behavior - Introduces full support for delta.tool_calls streaming from Harmony-compatible models - Adds parsing, incremental merging, and live updates of tool-call deltas in ChatService - Extends chat store, database schema, and message model to persist toolCalls content alongside reasoning traces - Implements new Svelte components ChatMessageToolCallBlock and ChatMessageToolCallItem for structured display of tool-call payloads - Adds a fallback raw string mode for malformed or non-JSON tool-call chunks - Adds 'Show tool call chunks' toggle in chat settings and new config flag showToolCalls - Updates ApiChatCompletion types to define ToolCall and ToolCallDelta interfaces for typed Harmony compatibility - Integrates tool-call rendering in ChatMessageAssistant when showToolCalls is enabled
|
Access the complete analysis in the LOCI Dashboard LLaMA.cpp Performance Analysis SummaryCritical Function Performance StatusAll core inference functions show zero performance degradation: • Function Modification Status: None of the critical functions were modified in this version. KPI Impact Analysis1. Tokens Per SecondImpact: None 2. Power ConsumptionImpact: Negligible (<0.001%) 3. Quantization EfficiencyImpact: None 4. Memory UsageImpact: None 5. Batch ProcessingImpact: None Root Cause AnalysisPerformance degradation source: The minimal degradation identified in the Action ItemsCode Optimization• No immediate action required - core functions maintain optimal performance Build System• Maintain current compiler optimization flags - no performance regressions detected Performance Monitoring• Baseline established - all critical functions show stable performance ConclusionThe version comparison reveals no meaningful performance impact on LLaMA.cpp's critical inference pipeline. All core functions maintain identical performance characteristics, with power consumption changes below measurement significance. The identified degradation in auxiliary functions does not affect inference throughput, memory efficiency, or quantization performance. |
DajanaV
force-pushed
the
main
branch
21 times, most recently
from
b655780 to
94ec54d
Compare
Mirrored from ggml-org/llama.cpp#16618
Close ggml-org/llama.cpp#16597