-
Notifications
You must be signed in to change notification settings - Fork 8.8k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
make/cmake: add missing force MMQ/cuBLAS for HIP
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8515
opened Jul 16, 2024 by
JohannesGaessler
Loading…
Fix func call tokens for internlm2
python
python script changes
#8506
opened Jul 16, 2024 by
RunningLeon
Loading…
2 of 4 tasks
docs: added AI Studio to the list of UIs [no ci]
#8505
opened Jul 16, 2024 by
SommerEngineering
Loading…
2 of 4 tasks
llama : disable context-shift for DeepSeek v2
#8501
opened Jul 16, 2024 by
ggerganov
Loading…
1 of 4 tasks
CUDA: MMQ code deduplication + iquant support
Nvidia GPU
Issues specific to Nvidia GPUs
python
python script changes
Review Complexity : High
Generally require indepth knowledge of LLMs or GPUs
#8495
opened Jul 15, 2024 by
JohannesGaessler
Loading…
examples : Rewrite pydantic_models_to_grammar_examples.py
examples
python
python script changes
#8493
opened Jul 15, 2024 by
maruel
Loading…
2 of 4 tasks
llama : change fallback type IQ4_NL -> Q4_0
examples
#8489
opened Jul 15, 2024 by
ggerganov
Loading…
1 of 4 tasks
ggml: Install ggml-cuda.h in HIPBLAS ggml build
#8480
opened Jul 14, 2024 by
65a
Loading…
2 of 4 tasks
chore : Fix vulkan related compiler warnings, add help text, improve CLI options
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8477
opened Jul 14, 2024 by
teleprint-me
Loading…
2 of 4 tasks
metal : add BF16 support
Review Complexity : High
Generally require indepth knowledge of LLMs or GPUs
convert_hf_to_gguf.py, convert_hf_to_gguf_update.py: Added Ukrainian tokens into string
python
python script changes
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8435
opened Jul 11, 2024 by
AragonerUA
Loading…
2 of 4 tasks
Add multiple derived adaptions hosting
examples
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
#8415
opened Jul 10, 2024 by
zhipenghan
Loading…
2 of 4 tasks
feat: Support Moore Threads GPU
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
#8383
opened Jul 9, 2024 by
yeahdongcn
Loading…
2 of 4 tasks
ggml : reading the runtime sve config of the cpu
ggml
changes relating to the ggml tensor library for machine learning
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8382
opened Jul 9, 2024 by
jdomke
Loading…
2 of 4 tasks
Tokenizer fixes
python
python script changes
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
testing
Everything test related
ggml: avoid rebuild of GGML graph for each token (#7456)
ggml
changes relating to the ggml tensor library for machine learning
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
server: Update public_simplechat/datautils.mjs
examples
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
server
#8362
opened Jul 8, 2024 by
brochure
Loading…
2 of 4 tasks
server : avoid breaking KV cache when prompt >= n_ctx (#6855)
examples
python
python script changes
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
server
#8359
opened Jul 8, 2024 by
prfd
Loading…
2 of 4 tasks
Adding models to the list in convert-hf-to-gguf-update.py
python
python script changes
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8357
opened Jul 8, 2024 by
perpendicularai
Loading…
2 of 4 tasks
fix and speed up compilaton
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8354
opened Jul 7, 2024 by
diimdeep
Loading…
build example/main.cpp as shared library and intercept token printing using FFI
demo
Demonstrate some concept or idea, not intended to be merged
examples
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
#8339
opened Jul 6, 2024 by
mtasic85
Loading…
llama.swiftui: Fix a small bug
examples
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8268
opened Jul 3, 2024 by
ho2103
Loading…
2 of 4 tasks
Fix false flags used in termux demo in README.md
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8252
opened Jul 2, 2024 by
Quantaindew
Loading…
2 of 4 tasks
Fixed the model conversion bug caused by minicpm's GQA structure。After testing minicpm's GQA, the converted model generates all <h>. This is because the number of k and v matrices of Gqa should be the same as kv_head, not the same as head/kv_head.
python
python script changes
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8249
opened Jul 2, 2024 by
LDLINGLINGLING
Loading…
2 of 4 tasks
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.