-
Notifications
You must be signed in to change notification settings - Fork 13.2k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
vulkan : incremental shader builds
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16341
opened Sep 29, 2025 by
Acly
Loading…
metal : dynamic simdgroups for MV kernels
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
#16340
opened Sep 29, 2025 by
ggerganov
Loading…
ggml-cpu : inspect -march and -mcpu to found the CPU
ggml
changes relating to the ggml tensor library for machine learning
#16333
opened Sep 29, 2025 by
angt
Loading…
Chatapi ignore empty sampling
examples
server
#16330
opened Sep 29, 2025 by
ServeurpersoCom
Loading…
Enable CUDA Graph usage for Nemotron Nano v2 (NemotronH)
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#16328
opened Sep 29, 2025 by
anavp-nvidia
Loading…
vulkan: in flash attention, bounds check against nem1 (don't rely on GGML_KQ_MASK_PAD)
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16316
opened Sep 28, 2025 by
jeffbolznv
Loading…
ggml : fix unaligned access in AMX code
ggml
changes relating to the ggml tensor library for machine learning
#16315
opened Sep 28, 2025 by
ggerganov
Loading…
ggml : remove SVE paths
ggml
changes relating to the ggml tensor library for machine learning
#16314
opened Sep 28, 2025 by
ggerganov
Loading…
ggml-backend : unify the dl_load_library() return type
ggml
changes relating to the ggml tensor library for machine learning
#16313
opened Sep 28, 2025 by
haiyuewa
Loading…
Enable Intel AMX acceleration while in CPU/GPU hybrid with new "--amx" toggle.
examples
#16310
opened Sep 28, 2025 by
Gadflyii
Loading…
cuda : Disable host buffers on integrated GPUs (#15034)
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#16308
opened Sep 28, 2025 by
ai-fonsi
Loading…
ci: Properly install rocwmma for hip builds
devops
improvements to build systems and github actions
#16305
opened Sep 28, 2025 by
IMbackK
Loading…
Add a deepwiki badge to auto-refresh the wiki-in-deepwiki weekly.
#16296
opened Sep 28, 2025 by
0400H
Loading…
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…
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…
webui : added download action (#13552)
examples
server
#16282
opened Sep 26, 2025 by
srogmann
Loading…
Update convert_hf_to_gguf_update.py
python
python script changes
#16280
opened Sep 26, 2025 by
cpumaxx
Loading…
Support FP16 as intermediate results in graph computation
ggml
changes relating to the ggml tensor library for machine learning
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.