Skip to content

Pull requests: PrismML-Eng/llama.cpp

New pull request New
8 Open 2 Closed
8 Open 2 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

(Performance) Optimized x86 and generic q1_0(_g128) dot ggml
#10 opened Apr 3, 2026 by pl752 Loading…
vulkan: add Q1_0_g128 (1-bit ternary) shader support ggml testing Vulkan
#9 opened Apr 3, 2026 by claudlos Loading…
3
fix: Q1_0_g128 x86 CPU kernel — float truncation + AVX2 vectorization ggml
#7 opened Apr 2, 2026 by wildcattrio Loading…
4 tasks done
4
fix: Q1_0_g128 x86 CPU kernel - correct output + AVX2/AVX-512 VNNI ggml
#6 opened Apr 2, 2026 by stfurkan Loading…
11
Fixes for CPU backend + instructions for targetting AMD GPUs ggml
#5 opened Apr 2, 2026 by philtomson Loading…
3
fix: Q1_0_g128 CPU dot product int truncation ggml
#4 opened Apr 2, 2026 by Marxist-Leninist Loading…
1
fix: Q1_0_g128 CPU kernel - correct output and AVX-512 SIMD ggml
#3 opened Apr 1, 2026 by jordankzf Loading…
6
feat: port TQ3_0 KV cache from llama-turboquant examples ggml Nvidia GPU
#2 opened Apr 1, 2026 by carlosfundora Loading…
5
ProTip! Exclude everything labeled bug with -label:bug.