Skip to content

Pull requests: kvcache-ai/ktransformers

New pull request New
7 Open 563 Closed
7 Open 563 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

[feat](kt-kernel): support avx2 only inference for bf16 fp8 and gptq int4
#1892 opened Mar 18, 2026 by mrhaoxx Loading…
2 tasks
52
[feat](kt-kernel): add --kt-numa-nodes for explicit NUMA node mapping
#1891 opened Mar 18, 2026 by ErvinXie Loading…
4 tasks done
3
support numa_binds,eg:numactl --physcpubind= --membind= python -m sgl…
#1890 opened Mar 18, 2026 by poryfly Loading…
2 tasks
5
[feat](kt-kernel): Add utility script to merge loose layer weights to safetensors
#1886 opened Mar 14, 2026 by DocShotgun Loading…
2 tasks done
9
[feat]: add expert bias support to AMX MoE kernel for gpt-oss-120B
#1862 opened Feb 23, 2026 by vshortt73 Loading…
4 of 5 tasks
1
9
CPU weight conversion for GLM-5 and MiniMax-M2.5 run-ci
#1853 opened Feb 17, 2026 by alin899992 Loading…
2 tasks done
9
[feat](kt-kernel): Load model from specified CPU cores
#1712 opened Dec 12, 2025 by raidshoebox1 • Draft
10
ProTip! no:milestone will show everything without a milestone.