Skip to content

Pull requests: GenerelSchwerz/llama.cpp

New pull request New
20 Open 54 Closed
20 Open 54 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

docs : link CLAUDE.md to AGENTS.md documentation Improvements or additions to documentation
#74 opened Sep 6, 2026 by GenerelSchwerz Owner Loading…
cuda: compile only the reachable native FlashAttention routes (follow-up to #55) CUDA devops documentation Improvements or additions to documentation ggml testing
#72 opened Sep 5, 2026 by Piggidragon • Draft
llama-bench: add kv-offload/workspace sweep flags documentation Improvements or additions to documentation examples
#70 opened Sep 4, 2026 by Piggidragon • Draft
4 tasks done
llama : add an attention split separate from the tensor split devops documentation Improvements or additions to documentation ggml testing
#69 opened Sep 3, 2026 by Piggidragon Loading…
1
kv-cache : spend the partial residency budget on the slowest link first testing
#68 opened Sep 3, 2026 by Piggidragon Loading…
1
kv-cache : resolve the partial KV residency set once for the model testing
#67 opened Sep 3, 2026 by Piggidragon Loading…
1
ggml-meta : split a host-resident KV cache by head devops documentation Improvements or additions to documentation ggml testing
#66 opened Sep 3, 2026 by Piggidragon Loading…
1
llama : split a tied output projection under split mode tensor testing
#65 opened Sep 3, 2026 by Piggidragon Loading…
1
ggml : report allocation failure from the meta buffer type ggml testing
#64 opened Sep 3, 2026 by Piggidragon Loading…
1
llama-bench placement flags, two host-KV fixes, and H1/H2/H3/H5/H13 measured documentation Improvements or additions to documentation examples ggml
#62 opened Sep 2, 2026 by Piggidragon • Draft
server : allow cache reuse for text-only prompts with mmproj loaded server
#60 opened Sep 1, 2026 by Piggidragon Loading…
2
cuda: optimize native quant FlashAttention integration (follow-up to #50)
#55 opened Aug 28, 2026 by GenerelSchwerz Owner Loading…
12
ggml-cuda: protect reused MoE cache slots
#47 opened Aug 26, 2026 by GenerelSchwerz Owner • Draft
ggml-cuda: coalesce contiguous staging copies
#46 opened Aug 26, 2026 by GenerelSchwerz Owner • Draft
ggml-cuda: prefetch overflow expert siblings
#45 opened Aug 26, 2026 by GenerelSchwerz Owner • Draft
ggml-cuda: reuse cached experts during overflow staging
#44 opened Aug 26, 2026 by GenerelSchwerz Owner • Draft
ggml-cuda: skip duplicate decode sibling prefetch
#43 opened Aug 26, 2026 by GenerelSchwerz Owner • Draft
ggml-cuda : reuse routing IDs across MoE siblings
#42 opened Aug 26, 2026 by GenerelSchwerz Owner • Draft
1 task done
sched: pipeline the delivery of a host-resident KV cache documentation Improvements or additions to documentation examples ggml testing
#39 opened Aug 26, 2026 by Piggidragon Loading…
2 tasks
6
kv: replace eligible dense causal masks with compact prefixes CUDA documentation Improvements or additions to documentation ggml server testing
#7 opened Aug 21, 2026 by GenerelSchwerz Owner Loading…
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.