-
Notifications
You must be signed in to change notification settings - Fork 9.6k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
llama.vim : add classic vim support [no ci]
examples
#9995
opened Oct 22, 2024 by
m18coppola
Loading…
2 of 4 tasks
cmake: force MSVC compiler charset to utf-8
build
Compilation issues
#9989
opened Oct 21, 2024 by
shou692199
Loading…
2 of 4 tasks
cmake: exclude libm.lib when GGML_SYCL=OFF but ONEAPI_ROOT is set in windows builds
#9983
opened Oct 21, 2024 by
shou692199
Loading…
2 of 4 tasks
[SYCL] Fix build on Windows when ccache enabled (#9954)
#9976
opened Oct 21, 2024 by
shou692199
Loading…
2 of 4 tasks
[CANN] Adapt to dynamically loadable backends mechanism
Ascend NPU
issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
#9970
opened Oct 21, 2024 by
leo-pony
Loading…
2 of 4 tasks
Add chat template for RWKV-World
python
python script changes
testing
Everything test related
#9968
opened Oct 21, 2024 by
MollySophia
Loading…
2 tasks done
LLamaCausalLM add support for tokenizer.json
python
python script changes
#9967
opened Oct 20, 2024 by
robbiemu
Loading…
llama : fix empty batch causing llama_batch_allocr to crash
#9966
opened Oct 20, 2024 by
ngxson
Loading…
2 of 4 tasks
add print cpu info
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#9957
opened Oct 20, 2024 by
NeoZhangJianyu
Loading…
2 of 4 tasks
nix: update flake.lock
nix
Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#9955
opened Oct 20, 2024 by
ggerganov
Loading…
Implementations for Q4_0_8_8 quantization based functions - RISC-V vector version
ggml
changes relating to the ggml tensor library for machine learning
lora : error message if new token is added in the adapter
python
python script changes
#9948
opened Oct 18, 2024 by
ngxson
Loading…
2 tasks done
ggml:metal Add POOL2D op and fix IM2COL in Metal backend for running MobileVLM_V2.
testing
Everything test related
#9943
opened Oct 18, 2024 by
junhee-yoo
Loading…
2 of 4 tasks
loader: use a map to find tensor by name from tensor weight
#9935
opened Oct 18, 2024 by
kylo5aby
Loading…
2 of 4 tasks
ggml : fix possible buffer use after free in sched reserve
ggml
changes relating to the ggml tensor library for machine learning
#9930
opened Oct 17, 2024 by
slaren
Loading…
sample: maintain token count in penalty sampler context
#9922
opened Oct 17, 2024 by
kylo5aby
Loading…
2 of 4 tasks
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels
examples
ggml
changes relating to the ggml tensor library for machine learning
#9921
opened Oct 17, 2024 by
chaxu01
Loading…
1 of 3 tasks
consolidated.safetensors
python
python script changes
#9916
opened Oct 16, 2024 by
CrispStrobe
Loading…
2 of 4 tasks
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
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
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.