Sync master with upstream release b9204#519
Merged
jan-service-account merged 14 commits intoMay 18, 2026
Merged
Conversation
* ngram : reduce noisy logs * ngram : reduce noisy logs
The --embd-normalize flag was registered only for the embedding and debug examples, so llama-server rejected it and the /embedding handler used a hard-coded default of 2 (L2). Add LLAMA_EXAMPLE_SERVER to the flag's example set and read params.embd_normalize as the handler's default. The per-request "embd_normalize" body field continues to override.
* common : remove atomic from json arguments * common : remove parsing logic on JSON arguments
* ci/run: set explicit SPIR-V Headers search path for macOS vulkan CI For whatever reason, the files are under additional sub-path `vulkan/` under the cmake directory, which does not match either current LunarG macOS Vulkan SDK structure (`lib/cmake/SPIRV-Headers`), nor what gets installed when you run the cmake build+install for SPIRV-Headers itself on at least Linux (`share/cmake/SPIRV-Headers`). This allows for SPIRV-Headers to be found, as currently the CI runner's setup does not seem to include the relevant path in list of search locations. * ggml-vulkan/CMakeLists: add a check for SPIRV-Headers This is installed by the project if it is built and installed. Receiving an error during the configuration step is generally preferred to receiving an error in the middle of a build.
…ers (ggml-org#23089) * common : delegate assistant continuation to template handler * server : implement echo parameter to exclude assistant prefill in the response * server : fix tests for prefill * server : use existing llama template * cont : clean up
* llama: avoid copying logits during prompt decode in MTP * review: update comment * llama-graph: call set_output for t_h_pre_norm
Cont of ggml-org#22936, forgot to update one site
Branch: ModalityConditionalAdapters AI-usage: none Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
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
12 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.
Updates dev branch with latest release (b9204) from ggml-org/llama.cpp