-
Notifications
You must be signed in to change notification settings - Fork 11.4k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Llama-3_1-Nemotron-Ultra-253B-v1 support
python
python script changes
#12843
opened Apr 9, 2025 by
ymcki
Loading…
[CANN]Support Opt LOG && MEAN && PAD_REFLECT_1D && STEP ...
ggml
changes relating to the ggml tensor library for machine learning
#12841
opened Apr 9, 2025 by
noemotiovon
Loading…
convert : write tensors in parallel
performance
Speed related topics
python
python script changes
#12837
opened Apr 8, 2025 by
compilade
Loading…
1 of 5 tasks
llamax : add a possible implementation of a simple API for llama.cpp …
build
Compilation issues
#12835
opened Apr 8, 2025 by
cyrilleberger
Loading…
Fixes #12823
ggml
changes relating to the ggml tensor library for machine learning
#12830
opened Apr 8, 2025 by
mehendarkarprajwal
Loading…
Add AVX512 implementation of GEMM - q4kx8
ggml
changes relating to the ggml tensor library for machine learning
#12829
opened Apr 8, 2025 by
Srihari-mcw
Loading…
convert : ability to lazy-load safetensors remotely without downloading to disk
python
python script changes
#12820
opened Apr 8, 2025 by
ngxson
Loading…
ci: fix cross-compile sync issues
devops
improvements to build systems and github actions
#12804
opened Apr 7, 2025 by
bandoti
Loading…
DeepSeek V2/V3 MLA implementation
python
python script changes
#12801
opened Apr 7, 2025 by
jukofyork
Loading…
opencl: fix couple crashes
ggml
changes relating to the ggml tensor library for machine learning
#12795
opened Apr 7, 2025 by
linehill
Loading…
SYCL: Add fp16 type support to unary op kernels
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#12788
opened Apr 7, 2025 by
qnixsynapse
Loading…
ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into the result register
ggml
changes relating to the ggml tensor library for machine learning
#12773
opened Apr 5, 2025 by
SongXiaoXi
Loading…
Added all CPU to Docker GPU images for 'token_embd.weight' compatibility
devops
improvements to build systems and github actions
#12749
opened Apr 4, 2025 by
rudiservo
Loading…
Update llama-quant.cpp llama_tensor_get_type with DeepSeek friendly modifications
ggml
changes relating to the ggml tensor library for machine learning
#12727
opened Apr 3, 2025 by
bartowski1182
Loading…
Fix: Abnormal exit on Android devices
ggml
changes relating to the ggml tensor library for machine learning
#12712
opened Apr 2, 2025 by
biyou
Loading…
[RFC][WIP] Common: Add an Initial Chat Memory Interface/Implementation
examples
server
#12698
opened Apr 1, 2025 by
markhpc
Loading…
WIP: Add support for CogAgent
examples
python
python script changes
server
#12679
opened Mar 31, 2025 by
Tianyue-Zhao
•
Draft
update changes relating to the ggml tensor library for machine learning
rope_multi
:
ggml
#12665
opened Mar 31, 2025 by
foldl
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:master.