LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Other

ktransformers

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

OtherEmerging

Stars

—

Forks

—

Contributors

8

Last push

13d ago

Recent commits

Latest commits.

Release/0.6.2.post3: carry kt-kernel SwiGLU clamp companion missing from post2
bb15fdfBenjamin F1mo ago
0.6.2.post2: submodule refactor and update tutorial (#1993)
37db9a3Benjamin F1mo ago
[fix]: add guard for SFT MoE and remove guard for AMX FP4 MoE on AVX512F+BW (#1980)
f7c4fa6Jim James1mo ago
docs(v4-flash): add optional AMXINT4 CPU-weight conversion path (#1986)
c465557Benjamin F1mo ago
docs(v4-flash): tilelang install, MTP flags, Ampere unsupported (#1979)
8b9d233Benjamin F

1mo ago

[release]: 0.6.2.post1

d7b5b49Benjamin F2mo ago

build: bump sglang submodule to c9edb75e0 (V4-Flash GPU prefill fallback fix + perf) (#1975)

9618997Benjamin F2mo ago

docs(v4-flash): pin transformers==4.57.1 in tutorial prerequisites (#1974)

088ed97Benjamin F2mo ago

Top contributors

Builders behind this project.