Weekly GitHub Report for Llama.cpp: May 11, 2026 - May 18, 2026 (14:40:37)
Weekly GitHub Report for Llama.cpp
Thank you for subscribing to our weekly newsletter! Each week, we deliver a comprehensive summary of your GitHub project's latest activity right to your inbox, including an overview of your project's issues, pull requests, contributors, and commit activity.
Table of Contents
I. News
1.1 Recent Version Releases:
The current version of this repository is b4991
1.2 Version Information:
The version released on March 29, 2025, introduces key updates that enhance overall performance and stability, with notable improvements in user interface responsiveness and security features. This release reflects a continued focus on optimizing user experience and safeguarding data integrity.
II. Issues
2.1 Top 5 Active Issues:
We consider active issues to be issues that that have been commented on most frequently within the last week. Bot comments are omitted.
As of our latest update, there are no active issues with ongoing comments this week.
2.2 Top 5 Stale Issues:
We consider stale issues to be issues that has had no activity within the last 30 days. The team should work together to get these issues resolved and closed as soon as possible.
As of our latest update, there are no stale issues for the project this week.
2.3 Open Issues
This section lists, groups, and then summarizes issues that were created within the last week in the repository.
Issues Opened This Week: 0
Summarized Issues:
As of our latest update, there are no open issues for the project this week.
2.4 Closed Issues
This section lists, groups, and then summarizes issues that were closed within the last week in the repository. This section also links the associated pull requests if applicable.
Issues Closed This Week: 2
Summarized Issues:
- Model transcription errors: The Qwen3-ASR model in version b8931 of llama.cpp produces incorrect transcriptions from audio input, indicating a problem with the model's output accuracy. A patched version corrects these transcription errors, demonstrating that the issue is fixable with modifications.
- issues/22357
- Evaluation parsing failures: The evaluation process encounters a bug where it fails to parse input at a specific position, causing server errors during the processing of certain XML-like tool call commands. This issue occurs on Linux systems using CUDA backends with NVIDIA GPUs, affecting model execution stability.
- issues/22422
2.5 Issue Discussion Insights
This section will analyze the tone and sentiment of discussions within this project's open and closed issues that occurred within the past week. It aims to identify potentially heated exchanges and to maintain a constructive project environment.
Based on our analysis, there are no instances of toxic discussions in the project's open or closed issues from the past week.
III. Pull Requests
3.1 Open Pull Requests
This section provides a summary of pull requests that were opened in the repository over the past week. The top three pull requests with the highest number of commits are highlighted as 'key' pull requests. Other pull requests are grouped based on similar characteristics for easier analysis. Up to 25 pull requests are displayed in this section, while any remaining pull requests beyond this limit are omitted for brevity.
Pull Requests Opened This Week: 0
As of our latest update, there are no open pull requests for the project this week.
3.2 Closed Pull Requests
This section provides a summary of pull requests that were closed in the repository over the past week. The top three pull requests with the highest number of commits are highlighted as 'key' pull requests. Other pull requests are grouped based on similar characteristics for easier analysis. Up to 25 pull requests are displayed in this section, while any remaining pull requests beyond this limit are omitted for brevity.
Pull Requests Closed This Week: 3
Key Closed Pull Requests
1. Support for DeepseekV32ForCausalLM with DeepSeek Sparse Attention (DSA): This pull request introduces initial support for DeepseekV32ForCausalLM models by implementing a proof-of-concept lightning indexer and DeepSeek Sparse Attention (DSA) with new GGML operations and KV cache structures, enabling CPU and CUDA backends while requiring further work to improve long context performance and validation through benchmarking.
- URL: pull/21149
- Associated Commits: a337e, e4676, 723f0, 72b72, 961bc, 9a63e, 3eb34, 08dc7, 998f4, 6c9d7, cb94b, 02c21, e7aa8, 1874a, 4309c, 9b0a4, 0ee5d, 7f557, 54945, 5677f, 1c830, 83a03, 6011b, 4aec6, a74d8, 5b9ce
- Associated Commits: a337e, e4676, 723f0, 72b72, 961bc, 9a63e, 3eb34, 08dc7, 998f4, 6c9d7, cb94b, 02c21, e7aa8, 1874a, 4309c, 9b0a4, 0ee5d, 7f557, 54945, 5677f, 1c830, 83a03, 6011b, 4aec6, a74d8, 5b9ce
2. ggml-vulkan/CMakeLists: add a check for SPIRV-Headers: This pull request adds a check in the ggml-vulkan CMakeLists to verify the presence of SPIRV-Headers at configure time, ensuring the build fails early if this required dependency is missing, thereby improving build reliability especially during cross-compilation scenarios.
- URL: pull/22009
- Associated Commits: 67cee
- Associated Commits: 67cee
3. llama: allow partial seq_rm for GDN models for speculative decoding: This pull request introduces a breaking change to the GDN API by enabling partial sequence rollback up to a specified draft_max during speculative decoding for GDN models, significantly improving efficiency by storing intermediate states and reducing redundant computation, resulting in approximately 1.8 times better performance on CPU and CUDA platforms.
- URL: pull/22400
- Associated Commits: 93325
- Associated Commits: 93325
3.3 Pull Request Discussion Insights
This section will analyze the tone and sentiment of discussions within this project's open and closed pull requests that occurred within the past week. It aims to identify potentially heated exchanges and to maintain a constructive project environment.
Based on our analysis, there are no instances of toxic discussions in the project's open or closed pull requests from the past week.
IV. Contributors
4.1 Contributors
Active Contributors:
We consider an active contributor in this project to be any contributor who has made at least 1 commit, opened at least 1 issue, created at least 1 pull request, or made more than 2 comments in the last month.
If there are more than 10 active contributors, the list is truncated to the top 10 based on contribution metrics for better clarity.
| Contributor | Commits | Pull Requests | Issues | Comments |
|---|---|---|---|---|
| TheTom | 97 | 0 | 0 | 0 |
| ggerganov | 49 | 0 | 0 | 0 |
| scutler-nv | 33 | 1 | 0 | 0 |
| gabe-l-hart | 26 | 0 | 0 | 0 |
| johndpope | 25 | 0 | 0 | 0 |
| michaelw9999 | 23 | 0 | 0 | 0 |
| No author found | 21 | 0 | 0 | 0 |
| max-krasnyansky | 21 | 0 | 0 | 0 |
| signalnine | 20 | 0 | 0 | 0 |
| njsyw1997 | 19 | 0 | 0 | 0 |