Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
479 Open 6,109 Closed
479 Open 6,109 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

model : gemma3n text-only
#14400 opened Jun 26, 2025 by ngxson Loading…
3
Add explanation to --no-mmap in llama server
#14399 opened Jun 26, 2025 by malte-j • Draft
cmake: regen vulkan shaders when shaders-gen sources change ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#14398 opened Jun 26, 2025 by bandoti Loading…
2
ggml : add pointer to attach user data ggml changes relating to the ggml tensor library for machine learning
#14397 opened Jun 26, 2025 by koush Loading…
SYCL: Take improvements from GLU branch and disable faulty fp16 exp kernel ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#14395 opened Jun 26, 2025 by qnixsynapse Loading…
4
compare-commits.sh: support both llama-bench and test-backend-ops python python script changes script Script related
#14392 opened Jun 26, 2025 by yeahdongcn Loading…
3
Add Conv2d for CPU ggml changes relating to the ggml tensor library for machine learning
#14388 opened Jun 26, 2025 by am17an Loading…
ggml-cpu: Build variant targeting Neoverse-V2 ggml changes relating to the ggml tensor library for machine learning
#14380 opened Jun 25, 2025 by ckastner Loading…
vulkan: handle noncontig in the final case of ggml_vk_get_cpy_pipeline ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#14378 opened Jun 25, 2025 by jeffbolznv Loading…
webui: preserve partial content when streaming errors occur examples server
#14374 opened Jun 25, 2025 by Aaryan-549 Loading…
5 of 8 tasks
1
Q2k interleaving implementation - x86/x64 SIMD ggml changes relating to the ggml tensor library for machine learning
#14373 opened Jun 25, 2025 by Srihari-mcw Loading…
docs: fix broken url in main readme
#14371 opened Jun 25, 2025 by justinclift-prvidr Loading…
5
test-backend-ops: add support for specifying output format testing Everything test related
#14368 opened Jun 25, 2025 by yeahdongcn Loading…
19
vulkan: Add fusion support for RMS_NORM+MUL ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#14366 opened Jun 24, 2025 by jeffbolznv • Draft
6
llama : add high-throughput mode Apple Metal https://en.wikipedia.org/wiki/Metal_(API) examples ggml changes relating to the ggml tensor library for machine learning
#14363 opened Jun 24, 2025 by ggerganov • Draft
11 of 19 tasks
2
CUDA: add bf16 and f32 support to cublas_mul_mat_batched ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#14361 opened Jun 24, 2025 by am17an Loading…
21
server : fix assistant prefilling when content is an array examples python python script changes server
#14360 opened Jun 24, 2025 by CISC Loading…
1
2
llama : expose C API to get layer device type
#14358 opened Jun 24, 2025 by okaris Loading…
build: refine toplevel .gitignore script Script related
#14355 opened Jun 24, 2025 by zhouwg Loading…
1 task done
Add script to test op perf and compare python python script changes script Script related
#14354 opened Jun 24, 2025 by yeahdongcn Loading…
@yeahdongcn
12
[server] webui DB import and export examples server
#14347 opened Jun 23, 2025 by feiloo Loading…
2
vulkan: Increase workgroup size for GLU, for performance ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#14345 opened Jun 23, 2025 by jeffbolznv Loading…
8
Make the shell scripts cross-platform devops improvements to build systems and github actions examples script Script related server SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related
#14341 opened Jun 23, 2025 by vedranmiletic Loading…
vulkan: lock accesses of pinned_memory vector ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#14333 opened Jun 22, 2025 by jeffbolznv Loading…
8
make "serve" library examples server
#14331 opened Jun 22, 2025 by arnej27959 Loading…
ProTip! Adding no:label will show everything without a label.