Skip to content

Pull requests: ggerganov/llama.cpp

New pull request New
334 Open 4,628 Closed
334 Open 4,628 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

ggml-cuda : add TQ2_0 kernels, for ternary inference on GPU enhancement New feature or request ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs performance Speed related topics python python script changes Review Complexity : High Generally require indepth knowledge of LLMs or GPUs testing Everything test related
#11183 opened Jan 10, 2025 by compilade Loading…
gguf-py: Fixed local detection of gguf pacakge python python script changes
#11180 opened Jan 10, 2025 by VJHack Loading…
1
convert : sort print supported models [no ci] python python script changes
#11179 opened Jan 10, 2025 by danbev Loading…
contrib : add naming guidelines
#11177 opened Jan 10, 2025 by ggerganov Loading…
5
SYCL: Add gated linear attention kernel ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#11175 opened Jan 10, 2025 by qnixsynapse Loading…
llama : update API names to use correct prefix android Issues specific to Android examples server testing Everything test related
#11174 opened Jan 10, 2025 by ggerganov Loading…
lora : update API names breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. examples server
#11167 opened Jan 9, 2025 by ggerganov Loading…
4
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#11166 opened Jan 9, 2025 by jeffbolznv Loading…
8
FR: server: Pre-fill textarea and auto-generate based on query parameters examples server
#11150 opened Jan 9, 2025 by tim-janik Loading…
7
vulkan: optimize coopmat2 q2_k dequant function ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#11130 opened Jan 7, 2025 by jeffbolznv Loading…
llama-bench : add test measuring token generation rate at given prompt length examples
#11126 opened Jan 7, 2025 by fairydreaming Loading…
5
llama : functions -> methods android Issues specific to Android breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. devops improvements to build systems and github actions examples python python script changes server testing Everything test related
#11110 opened Jan 6, 2025 by ggerganov Loading…
2 tasks done
7
feat(ci): add visionOS build workflow devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning
#11103 opened Jan 6, 2025 by ggerganov Loading…
1
vulkan: scale caching for k quants + misc fixes ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#11081 opened Jan 5, 2025 by netrunnereve Loading…
26
Remove obsolete HIP workaround build Compilation issues devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment Nvidia GPU Issues specific to Nvidia GPUs
#11080 opened Jan 5, 2025 by sARY77 Loading…
3
server : POC OAI-compat TTS using OuteTTS examples server
#11070 opened Jan 3, 2025 by ngxson Loading…
10
feat(ci): add visionOS build workflow devops improvements to build systems and github actions
#11065 opened Jan 3, 2025 by sinkingsugar Loading…
1
llama : remove notion of CLS token python python script changes
#11064 opened Jan 3, 2025 by ggerganov Loading…
2
android : Apply chat template android Issues specific to Android examples
#11059 opened Jan 3, 2025 by Dhruvanand24 Loading…
CUDA Graph Compute Function Refactor (precursor for performance improvements) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#11042 opened Jan 2, 2025 by aendk Loading…
5
Add VisionOS compatibility by adding missing type definitions Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#11019 opened Dec 30, 2024 by sinkingsugar Loading…
5
Add Jinja template support examples python python script changes script Script related server
#11016 opened Dec 30, 2024 by ochafik • Draft
3 tasks
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…
16
Removed unnecessary iteration of batch n_tokens on sequence embedding… examples
#10972 opened Dec 25, 2024 by Emreerdog 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
ProTip! Adding no:label will show everything without a label.