Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
443 Open 5,588 Closed
443 Open 5,588 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

vulkan: enable fp16 for gcn 3 and 4 chips ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#13396 opened May 9, 2025 by netrunnereve • Draft
llama : do not crash if there is no CPU backend examples
#13395 opened May 8, 2025 by slaren Loading…
grammar: handle misplaced special regex chars [*+?]
#13391 opened May 8, 2025 by rick-github Loading…
1
Add --parse-special for enabling parsing of special tokens in imatrix calculation examples
#13389 opened May 8, 2025 by bartowski1182 Loading…
metal : optimize MoE for large batches Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#13388 opened May 8, 2025 by ggerganov Loading…
Add --disable-op-offload to improve -ot pp perf in MoE models like llama4 400B examples ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#13386 opened May 8, 2025 by hjc4869 Loading…
2
arg : add model catalog
#13385 opened May 8, 2025 by ngxson • Draft
7
CUDA: fix crash on large batch size for MoE models ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13384 opened May 8, 2025 by JohannesGaessler Loading…
1
1
sycl: simplify bin_bcast_kernel ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13383 opened May 8, 2025 by AD2605 Loading…
musa: enable MUSA graphs ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13382 opened May 8, 2025 by yeahdongcn • Draft
2
gguf-py: Optimize GGUFReader read-only mode performance python python script changes
#13378 opened May 8, 2025 by Isotr0py Loading…
1
llama-run: add support for downloading models from ModelScope examples
#13370 opened May 8, 2025 by yeahdongcn Loading…
1
llama: Fix typos in multiple files ggml changes relating to the ggml tensor library for machine learning Kompute https://github.com/KomputeProject/kompute/ python python script changes SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13369 opened May 8, 2025 by co63oc Loading…
CUDA: update build CTK version to 12.8 devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13360 opened May 7, 2025 by thevishalagarwal Loading…
SYCL: Fix test-backend-ops crashes with SYCL-Graph ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13357 opened May 7, 2025 by EwanC • Draft
rpc : add rpc_msg_set_tensor_hash_req ggml changes relating to the ggml tensor library for machine learning
#13353 opened May 7, 2025 by rgerganov Loading…
2
common: add default reranker presets
#13352 opened May 7, 2025 by ca1yz Loading…
1
python : bump transformers version python python script changes
#13351 opened May 7, 2025 by ngxson Loading…
Add mistral-chat-7b preset for llama-server examples
#13348 opened May 7, 2025 by vahedshaik Loading…
Support Sp token Function Call Token Implementation
#13339 opened May 6, 2025 by glide-the Loading…
1
llama: move page cache via mbind to prevent cross-NUMA access
#13335 opened May 6, 2025 by vishalc-ibm Loading…
1
add AMD Genoa ggml changes relating to the ggml tensor library for machine learning
#13334 opened May 6, 2025 by QuPengfei Loading…
vulkan: Allow up to 4096 elements for mul_mat_id row_ids ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#13326 opened May 6, 2025 by jeffbolznv Loading…
6
vulkan: scalar flash attention implementation devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#13324 opened May 6, 2025 by jeffbolznv Loading…
40
[Perf] [CPU] eliminate redundant memory access in group query attention ggml changes relating to the ggml tensor library for machine learning
#13319 opened May 5, 2025 by ZelinMa557 Loading…
7
ProTip! Updated in the last three days: updated:>2025-05-06.