Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
405 Open 5,259 Closed
405 Open 5,259 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

convert : BailingMoE : fix qkv split when head_dim is 0 python python script changes
#12687 opened Apr 1, 2025 by CISC Loading…
Fix clang warning in gguf_check_reserved_keys ggml changes relating to the ggml tensor library for machine learning
#12686 opened Apr 1, 2025 by yeahdongcn Loading…
1
vulkan: fix build when glslc doesn't support coopmat ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12683 opened Apr 1, 2025 by wbruna Loading…
gguf-split now respects dry-run option examples
#12681 opened Mar 31, 2025 by nickhuang99 Loading…
1
WIP: Add support for CogAgent examples python python script changes server
#12679 opened Mar 31, 2025 by Tianyue-Zhao • Draft
vocab : BailingMoE : change possessive quantifiers to greedy
#12677 opened Mar 31, 2025 by CISC Loading…
4
use LLM_KV instead of gguf_find_key
#12672 opened Mar 31, 2025 by jklincn Loading…
[CANN]get_rows and dup optimization Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#12671 opened Mar 31, 2025 by noemotiovon Loading…
@hipudding @noemotiovon
update rope_multi: ggml changes relating to the ggml tensor library for machine learning
#12665 opened Mar 31, 2025 by foldl Loading…
contrib: support modelscope community examples
#12664 opened Mar 31, 2025 by tastelikefeet Loading…
17
llama : nit, DeepSeek V1 MoE is 16B and GigaChat is 20B
#12652 opened Mar 30, 2025 by CISC Loading…
opencl : fix memory allocation size ggml changes relating to the ggml tensor library for machine learning
#12649 opened Mar 30, 2025 by sparkleholic Loading…
2
tts : implement sesame CSM + Mimi decoder examples python python script changes
#12648 opened Mar 29, 2025 by ngxson Loading…
14
llama-server : implement universal assisted decoding examples server
#12635 opened Mar 28, 2025 by g2mt Loading…
vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12630 opened Mar 28, 2025 by jeffbolznv Loading…
2
vulkan: Implement split_k for coopmat2 flash attention. ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#12627 opened Mar 28, 2025 by jeffbolznv Loading…
opencl: remove a self-referential macro ggml changes relating to the ggml tensor library for machine learning
#12626 opened Mar 28, 2025 by linehill Loading…
sycl: allow ggml-sycl configuration and compilation using Visual Studio project/solution documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#12625 opened Mar 28, 2025 by s-Nick Loading…
12
opencl: Add support for multiple devices ggml changes relating to the ggml tensor library for machine learning
#12622 opened Mar 28, 2025 by linehill • Draft
Enable MMA for BF16 data types on Powerpc ggml changes relating to the ggml tensor library for machine learning
#12565 opened Mar 25, 2025 by shalinib-ibm • Draft
2
vulkan: Implement grouped query attention in the coopmat2 FA shader ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12559 opened Mar 25, 2025 by jeffbolznv Loading…
ggml-quants : weighted rounding algorithms with cumulative search generation quality Quality of model output ggml changes relating to the ggml tensor library for machine learning Less than 4 bits Efforts related to viable quantized models using <4 bits research 🔬 Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level Tensor Encoding Scheme https://github.com/ggerganov/llama.cpp/wiki/Tensor-Encoding-Schemes
#12557 opened Mar 25, 2025 by compilade • Draft
9
Draft: vulkan: Add bfloat16 support ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12554 opened Mar 24, 2025 by jeffbolznv Loading…
2
llama-map to support hugepage feature of pagesize 2M or 1G which can …
#12552 opened Mar 24, 2025 by nickhuang99 Loading…
Vulkan: Remove dedicated aligned matrix matrix multiplication shaders ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#12515 opened Mar 22, 2025 by 0cc4m • Draft
6
ProTip! Updated in the last three days: updated:>2025-03-29.