Skip to content

Pull requests: ggerganov/llama.cpp

New pull request New
306 Open 4,208 Closed
306 Open 4,208 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

nix: update flake.lock nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#10243 opened Nov 10, 2024 by ggerganov Loading…
server : (web UI) add copy button for code block, fix api key examples server
#10242 opened Nov 9, 2024 by ngxson Loading…
2 tasks done
server: Add back samplers examples server
#10239 opened Nov 9, 2024 by MaggotHATE Loading…
2 of 4 tasks
2
metal : refactor kernel args into structs ggml changes relating to the ggml tensor library for machine learning
#10238 opened Nov 9, 2024 by ggerganov • Draft
2 of 4 tasks
2
server : enable KV cache defrag by default examples server
#10233 opened Nov 9, 2024 by ggerganov Loading…
llama : use ggml_backend_dev_get_extra_bufts
#10228 opened Nov 9, 2024 by danbev Loading…
2 tasks done
vulkan: Fix newly added tests for permuted mul_mat and 1D im2col ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#10226 opened Nov 9, 2024 by jeffbolznv Loading…
2 of 4 tasks
4
support for llguidance grammars
#10224 opened Nov 9, 2024 by mmoskal • Draft
vulkan: Throttle the number of shader compiles during the build step
#10222 opened Nov 8, 2024 by jeffbolznv Loading…
2 of 4 tasks
1
metal : use F16 math in mul_mat kernels
#10220 opened Nov 8, 2024 by ggerganov • Draft
ci: add Ascend CANN build devops improvements to build systems and github actions
#10217 opened Nov 8, 2024 by xuedinge233 • Draft
CANN Support Ascend310P to accelerate F32 and F16 LLM Model Ascend NPU issues specific to Ascend NPUs enhancement New feature or request
#10216 opened Nov 8, 2024 by leo-pony Loading…
2 of 4 tasks
AVX BF16 and single scale quant optimizations ggml changes relating to the ggml tensor library for machine learning
#10212 opened Nov 8, 2024 by netrunnereve Loading…
2 of 4 tasks
docs: add doxygen documentation build Compilation issues
#10209 opened Nov 8, 2024 by sparkleholic Loading…
2 of 4 tasks
Draft: vulkan: Add VK_NV_cooperative_matrix2 support for mul_mat and FlashAttention2 ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#10206 opened Nov 7, 2024 by jeffbolznv Loading…
2 of 4 tasks
4
Introduce IQ4_NL_4_4 format and its neon implementation examples ggml changes relating to the ggml tensor library for machine learning
#10196 opened Nov 6, 2024 by FanShupei Loading…
2 of 4 tasks
9
CUDA: always create events for split buffers Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level
#10185 opened Nov 5, 2024 by JohannesGaessler Loading…
1
3
Introduce New Lookup-Table(LUT)-Based Matrix Multiplication Method ggml changes relating to the ggml tensor library for machine learning python python script changes
#10181 opened Nov 5, 2024 by QingtaoLi1 Loading…
2 of 4 tasks
4
gguf-py: Improve GGUFReader read-only mode performance python python script changes
#10159 opened Nov 4, 2024 by Isotr0py Loading…
2 of 4 tasks
main : add new feature: special commands demo Demonstrate some concept or idea, not intended to be merged examples
#10145 opened Nov 3, 2024 by ngxson • Draft
2 tasks done
12
Fix docker locale issue (#6267) devops improvements to build systems and github actions
#10142 opened Nov 2, 2024 by fyun89 Loading…
2 of 4 tasks
2
llama-bench : skip repeated values in consecutive lines examples
#10140 opened Nov 2, 2024 by slaren • Draft
ggml : skip register metal backend on os simulator ggml changes relating to the ggml tensor library for machine learning
#10132 opened Nov 2, 2024 by jhen0409 Loading…
2 of 4 tasks
2
Add user-provided tokenizer/detokenizer functionality examples
#10131 opened Nov 2, 2024 by ilan-theodoro Loading…
2 of 4 tasks
1
Server: handle generation until context is filled examples python python script changes server
#10128 opened Nov 1, 2024 by VJHack Loading…
2 of 4 tasks
5
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.