-
Notifications
You must be signed in to change notification settings - Fork 9.5k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
llama : bump max layers from 512 to 1024
#9910
opened Oct 16, 2024 by
nicoboss
Loading…
2 of 4 tasks
vulkan : improve ggml_vk_create_buffer error handling
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#9898
opened Oct 15, 2024 by
FanShupei
Loading…
2 of 4 tasks
llava : fix typo in error message [no ci]
examples
#9884
opened Oct 14, 2024 by
danbev
Loading…
2 of 4 tasks
fix: use changes relating to the ggml tensor library for machine learning
vm_allocate
to allocate CPU backend buffer on macOS
ggml
#9875
opened Oct 14, 2024 by
giladgd
Loading…
2 of 4 tasks
llama : add nvidia nemotron chat template (not-working due to bad tokenizer)
testing
Everything test related
New quant strategy / FTYPE IQ3_XL 4bpw
examples
python
python script changes
#9855
opened Oct 12, 2024 by
Nexesenex
Loading…
2 of 4 tasks
llama : adds llama-grammar memoization stacks (#4218)
examples
testing
Everything test related
#9833
opened Oct 11, 2024 by
clarismiranda
Loading…
2 of 4 tasks
llama.cpp : fix --leave-output-tensor for llama-quantize.
#9829
opened Oct 10, 2024 by
drollings
Loading…
2 of 4 tasks
fix gguf-py: Conversion error when multiple licenses are configured
python
python script changes
#9807
opened Oct 9, 2024 by
mmngays
Loading…
2 of 4 tasks
fix logging in examples/main/main.cpp
examples
#9795
opened Oct 8, 2024 by
fuzzybritches0
Loading…
1 of 3 tasks
llama.vim : plugin for Neovim
examples
server
#9787
opened Oct 8, 2024 by
ggerganov
Loading…
5 of 7 tasks
Added support for SFTTrainer checkpoint models and adapter models containing some non-LoRA weights
python
python script changes
#9778
opened Oct 8, 2024 by
Victoran0
Loading…
2 of 4 tasks
[gguf-py] gguf_reader: numpy 2 newbyteorder fix
python
python script changes
#9772
opened Oct 7, 2024 by
jettjaniak
Loading…
2 of 4 tasks
ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model.
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#9763
opened Oct 6, 2024 by
cyzero-kim
Loading…
2 of 4 tasks
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch
android
Issues specific to Android
breaking change
Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility.
examples
server
#9745
opened Oct 4, 2024 by
ngxson
Loading…
2 tasks done
vulkan : add GGML_VK_FORCE_HEAP_INDEX env var
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#9734
opened Oct 4, 2024 by
gyf304
Loading…
2 of 4 tasks
Don't use a specific version for the main-cmake-pkg (CMake throws and error)
examples
#9730
opened Oct 3, 2024 by
ukicomputers
Loading…
2 of 4 tasks
vulkan : add backend registry / device interfaces
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#9721
opened Oct 3, 2024 by
slaren
Loading…
[SYCL] Add SYCL Backend registry, device and Event Interfaces
examples
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#9705
opened Oct 1, 2024 by
OuadiElfarouki
Loading…
2 of 4 tasks
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.