Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
425 Open 5,459 Closed
425 Open 5,459 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

mtmd : fix glm-edge redundant token count examples
#13139 opened Apr 27, 2025 by ngxson Loading…
llama : (mrope) allow using normal 1D position for text token examples
#13138 opened Apr 27, 2025 by ngxson Loading…
1
CUDA: fix q_nope_absorbed precision for Deepseek 2 Lite f16 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13137 opened Apr 27, 2025 by JohannesGaessler Loading…
clip : refactor set input for cgraph examples
#13136 opened Apr 27, 2025 by ngxson Loading…
1
CUDA: build archs as virtual for GGML_NATIVE=OFF ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13135 opened Apr 27, 2025 by JohannesGaessler Loading…
1
convert : improve model arch handling python python script changes
#13122 opened Apr 26, 2025 by ngxson Loading…
7
sycl : Implemented reorder Q4_K mmvq ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13109 opened Apr 25, 2025 by sgeor255 Loading…
1 task
1
context : allow cache-less context for embeddings examples server
#13108 opened Apr 25, 2025 by ggerganov • Draft
ggml-backend : add load_tensor() to backend API Apple Metal https://en.wikipedia.org/wiki/Metal_(API) examples ggml changes relating to the ggml tensor library for machine learning Kompute https://github.com/KomputeProject/kompute/ Nvidia GPU Issues specific to Nvidia GPUs SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language Vulkan Issues specific to the Vulkan backend
#13106 opened Apr 25, 2025 by rgerganov • Draft
4
[sync #10544] llama/ggml: add LLM training support examples ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#13105 opened Apr 25, 2025 by ggerganov • Draft
1 task
1
[CANN] Simplify the environment variable setting for GGML_CANN_MEM_POOL and GGML_CANN_ASYNC_MODE Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#13104 opened Apr 25, 2025 by bachelor-dou Loading…
@bachelor-dou
1
fix wrong template in GLM4-0414 python python script changes
#13099 opened Apr 24, 2025 by matteoserva Loading…
19
llama-bench: add -d depth arg examples
#13096 opened Apr 24, 2025 by thevishalagarwal Loading…
8
ggml: Implement yield barrier using futex for improved thread scheduling efficiency ggml changes relating to the ggml tensor library for machine learning
#13079 opened Apr 23, 2025 by SongXiaoXi Loading…
1
SYCL: Add all missing unary kernels ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13074 opened Apr 23, 2025 by qnixsynapse Loading…
10
Reduce enum sizes some are used in structs, which allowed them to be optimized. build Compilation issues ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language Vulkan Issues specific to the Vulkan backend
#13071 opened Apr 22, 2025 by GermanAizek Loading…
22
fix(rpc): Improve input validation and error handling ggml changes relating to the ggml tensor library for machine learning
#13069 opened Apr 22, 2025 by thevilledev Loading…
1
33
Fix ChatGLMModel for glm-4-9b cannot find tokenizer merges in model file python python script changes
#13058 opened Apr 22, 2025 by glide-the Loading…
9
Update README.md for tts example to use afplay on MacOS examples
#13056 opened Apr 22, 2025 by maxxam1221 Loading…
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel ggml changes relating to the ggml tensor library for machine learning
#13053 opened Apr 21, 2025 by eddnjjn Loading…
11
[CANN]Support OP MUL_MAT_ID Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#13042 opened Apr 21, 2025 by noemotiovon Loading…
@noemotiovon
quantize: Handle user-defined pruning of whole layers (blocks) examples
#13037 opened Apr 20, 2025 by EAddario • Draft
gguf-py : avoid requiring PySide6 for packaged scripts bugfix fixes an issue or bug devops improvements to build systems and github actions nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment python python script changes
#13036 opened Apr 20, 2025 by compilade Loading…
1
4
quantize: improve pattern matching for allowed tensors examples
#13033 opened Apr 20, 2025 by EAddario Loading…
Bitnet: directly use scale instead of inverting it twice python python script changes
#13026 opened Apr 19, 2025 by viraatdas Loading…
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.