Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
716 Open 8,954 Closed
716 Open 8,954 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

cuda : enable CUDA graphs for MMID 1 <= BS <= 4 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#19645 opened Feb 15, 2026 by ggerganov Loading…
1 task
2
graph : fix KQ mask, lora, cvec reuse checks
#19644 opened Feb 15, 2026 by ggerganov Loading…
common : fix Step-3.5-Flash format detection and thinking support testing Everything test related
#19635 opened Feb 15, 2026 by jesseposner Loading…
2
Vulkan Scalar Flash Attention Refactor ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19625 opened Feb 14, 2026 by 0cc4m • Draft
6
[server] save generated text for the /slots endpoint (for LLAMA_SERVER_SLOTS_DEBUG=1) examples server
#19622 opened Feb 14, 2026 by matteoserva Loading…
Fix gpt-oss tool calling: pass tool args and tool responses as json
#19620 opened Feb 14, 2026 by matteoserva Loading…
1
3
[WIP] refactor llama-quant.cpp examples
#19616 opened Feb 14, 2026 by ddh0 • Draft
opencl: optimize mean and sum_row kernels ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#19614 opened Feb 14, 2026 by shaofeiqi • Draft
fix: GLM 4.5 streaming tool-call parsing + grammar error handling examples server testing Everything test related
#19612 opened Feb 14, 2026 by Gunther-Schulz Loading…
Add support for Tiny Aya Models python python script changes
#19611 opened Feb 14, 2026 by saurabhdash2512 Loading…
3
ggml: ggml-cpu: force-no-lto-for-cpu-feats ggml changes relating to the ggml tensor library for machine learning
#19609 opened Feb 13, 2026 by talhaHavadar Loading…
2
llama : add group feature to split-mode to minimize GPU spread for running a model examples server
#19608 opened Feb 13, 2026 by dan-and Loading…
metal: use mul_mv_ext for large n on non-simdgroup_mm GPUs Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#19600 opened Feb 13, 2026 by ai-janitor Loading…
3 of 4 tasks
models : deduplicate delta-net graphs for Qwen family model Model specific
#19597 opened Feb 13, 2026 by ggerganov Loading…
2 tasks
4
mtmd : chat : Fix extra \n between text and media marker examples server
#19595 opened Feb 13, 2026 by tdakhran Loading…
11
Add a build target to generate ROCm artifacts using ROCm 7.11 devops improvements to build systems and github actions
#19594 opened Feb 13, 2026 by superm1 Loading…
8
docs : explicit about banning accounts that violates policy
#19593 opened Feb 13, 2026 by ngxson Loading…
8
Adjust workaround for ROCWMMA_FATTN/GFX9 to only newer ROCm veresions ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#19591 opened Feb 13, 2026 by superm1 Loading…
1
1
WASM Relaxed SIMD Enhancement ggml changes relating to the ggml tensor library for machine learning
#19590 opened Feb 13, 2026 by JeremyCEY Loading…
hexagon : fix build release (#19444) build Compilation issues
#19587 opened Feb 13, 2026 by mengshengwu Loading…
1
1
server: add Anthropic-compatible cache_read_input_tokens to usage metrics examples python python script changes server
#19572 opened Feb 12, 2026 by wrapss Loading…
1 task done
[CMake] Enable test-chat out of tree build testing Everything test related
#19558 opened Feb 12, 2026 by jplehr Loading…
webui: add lazy markdown loading for improved performance examples server
#19557 opened Feb 12, 2026 by shem-aleph Loading…
1 task done
templates : fix double-escaping in gpt-oss tool call arguments and responses
#19553 opened Feb 12, 2026 by yurekami Loading…
3 tasks
1
make ggml_is_view as API ggml changes relating to the ggml tensor library for machine learning
#19539 opened Feb 12, 2026 by foldl Loading…
4
ProTip! Adding no:label will show everything without a label.