Skip to content

Pull requests: ggerganov/llama.cpp

New pull request New
331 Open 4,550 Closed
331 Open 4,550 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add support for QRWKV6 hybrid models & slight optimization for RWKV6 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#11001 opened Dec 28, 2024 by MollySophia Loading…
vulkan: experimental coalesced read to shared memory before dequantization ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#10999 opened Dec 27, 2024 by netrunnereve • Draft
2
server : fix token duplication when streaming with stop strings examples server
#10997 opened Dec 27, 2024 by z80maniac Loading…
1
server: added more docs for response_fields field examples server
#10995 opened Dec 27, 2024 by isaac-mcfadyen Loading…
server : allow using LoRA adapters per-request examples python python script changes server
#10994 opened Dec 27, 2024 by ngxson • Draft
2 tasks
1
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON examples ggml changes relating to the ggml tensor library for machine learning
#10992 opened Dec 27, 2024 by peter277 Loading…
draft: vulkan: optimize mul_mat for small values of N ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#10991 opened Dec 26, 2024 by jeffbolznv Loading…
1
4
Vulkan: Destroy Vulkan instance on exit ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#10989 opened Dec 26, 2024 by 0cc4m Loading…
7
vulkan: Use push constant offset to handle misaligned descriptors ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#10987 opened Dec 26, 2024 by jeffbolznv Loading…
ggml : fix undefined reference to std::filesystem(#10978) ggml changes relating to the ggml tensor library for machine learning
#10979 opened Dec 26, 2024 by Clauszy Loading…
3
server : add OAI compat for /v1/completions breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. examples python python script changes server
#10974 opened Dec 25, 2024 by ngxson Loading…
2 tasks done
Removed unnecessary iteration of batch n_tokens on sequence embedding… examples
#10972 opened Dec 25, 2024 by Emreerdog Loading…
Cosine similarity is undefined when any vector is zero.
#10968 opened Dec 24, 2024 by AndyM3 Loading…
1
server : (web ui) Enable gzip compression for local storage demo Demonstrate some concept or idea, not intended to be merged examples server
#10945 opened Dec 22, 2024 by exxocism Loading…
2 tasks
3
vulkan: im2col and matmul optimizations for stable diffusion ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#10942 opened Dec 22, 2024 by jeffbolznv Loading…
3
Allow user to compile with any cuda version using github actions devops improvements to build systems and github actions
#10928 opened Dec 21, 2024 by jianlins Loading…
1
llamafile_sgemm API - INT8 implementation ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#10912 opened Dec 20, 2024 by amritahs-ibm Loading…
26
llama : refactor src/llama.cpp devops improvements to build systems and github actions examples server
#10902 opened Dec 19, 2024 by ggerganov • Draft
3 tasks
1
llama : add support for Cohere2ForCausalLM python python script changes
#10900 opened Dec 19, 2024 by dranger003 Loading…
1
10
ASCII/Romanization for OuteTTS Multilingual Processing demo Demonstrate some concept or idea, not intended to be merged examples
#10894 opened Dec 19, 2024 by edwko Loading…
4
llama: Ensure KV cache is fully defragmented.
#10873 opened Dec 17, 2024 by jessegross Loading…
SYCL: Fixes for building SYCL backend for AMD GPUs documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#10851 opened Dec 16, 2024 by lhl Loading…
9
Fix compilation on Pop!_OS 22.04 LTS CUDA ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#10835 opened Dec 15, 2024 by mika314 Loading…
5
add ggml_backend_sched_dump_dot ggml changes relating to the ggml tensor library for machine learning
#10825 opened Dec 14, 2024 by foldl Loading…
10
Bamba architecture Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning python python script changes testing Everything test related
#10810 opened Dec 12, 2024 by gabe-l-hart • Draft
3 tasks
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.