Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
549 Open 7,119 Closed
549 Open 7,119 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

tests: override test_set_rows::max_nmse_err to allow for occasional rounding differences testing Everything test related
#16295 opened Sep 28, 2025 by jeffbolznv Loading…
ci: update vulkan ci devops improvements to build systems and github actions
#16294 opened Sep 27, 2025 by netrunnereve Loading…
vulkan: Fix validation failure in quantized flash attention ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16292 opened Sep 27, 2025 by jeffbolznv Loading…
hip : substituted bpermute ops with swizzle ops (gfx906, maybe all AMD) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16291 opened Sep 27, 2025 by iacopPBK Loading…
2
webui : added download action (#13552) examples server
#16282 opened Sep 26, 2025 by srogmann Loading…
4
Update convert_hf_to_gguf_update.py python python script changes
#16280 opened Sep 26, 2025 by cpumaxx Loading…
3
rpc : add support for multiple devices examples ggml changes relating to the ggml tensor library for machine learning
#16276 opened Sep 26, 2025 by rgerganov • Draft
1
4
Support FP16 as intermediate results in graph computation ggml changes relating to the ggml tensor library for machine learning
#16270 opened Sep 26, 2025 by hipudding • Draft
@hipudding
musa: update compile flags ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16265 opened Sep 26, 2025 by yeahdongcn Loading…
1
common : fix reasoning before forced tool call via tool_choice = required
#16264 opened Sep 26, 2025 by crat0z Loading…
4
Correct XTC threshold args documentation
#16260 opened Sep 25, 2025 by Volko61 Loading…
Refactor llama-model.cpp
#16252 opened Sep 25, 2025 by pwilkin Loading…
3
CANN: Update several operators to support FP16 data format Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#16251 opened Sep 25, 2025 by hipudding Loading…
@hipudding
3
ci : add AMD runners and workflows devops improvements to build systems and github actions
#16249 opened Sep 25, 2025 by ggerganov Loading…
13
kleidiai: fix work size and threads sync for fp16 ggml changes relating to the ggml tensor library for machine learning
#16246 opened Sep 25, 2025 by chaxu01 Loading…
llama : merge logit and p fields in llama_token_data examples server testing Everything test related
#16241 opened Sep 25, 2025 by danbev • Draft
1
ggml-cpu: detect correct cpu flags for arm64 (#16229) ggml changes relating to the ggml tensor library for machine learning
#16239 opened Sep 25, 2025 by lizhenneng Loading…
1
1
Update the docs on -t --threads examples server
#16236 opened Sep 24, 2025 by takasurazeem Loading…
3
Extend CI for i8mm kernels as well testing Everything test related
#16234 opened Sep 24, 2025 by Rohanjames1997 Loading…
1
metal : extend mat-mat multiplication support Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#16225 opened Sep 24, 2025 by ggerganov Loading…
Improve Mobile UI for dialogs and action dropdowns examples server
#16222 opened Sep 24, 2025 by allozaur Loading…
1
1
HIP: Disable ROCWMMA fattn on CDNA when compiled against ROCWMMA 2.0.0 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16221 opened Sep 24, 2025 by IMbackK Loading…
10
Model: Granite docling + Idefics3 preprocessing (SmolVLM) examples python python script changes
#16206 opened Sep 23, 2025 by gabe-l-hart Loading…
1
8
vulkan: Add ACC_TYPE_VEC2 implementation ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16203 opened Sep 23, 2025 by SavicStefan Loading…
1
tools/main: llama-cli: prevent spurious assistant token (#13402) examples
#16202 opened Sep 23, 2025 by vinkal-chudgar Loading…
1
3
ProTip! Follow long discussions with comments:>50.