Eric BuehlerandGitHub e4a8222d6f Add the Qwen 3 and Qwen 3 MoE models! (#1285) ...

* Add qwen3 model

* Add enable_thinking

* Add initial qwen3 moe

* Add the moe model

* Format

* Fix order of norm

* Fix expert shapes

* Fix reverse

* Fix norm device for isq

* Fix nonzero when no nonzero

* Moe model runs

* Working qwen3 moe

* Add metal fp8 blockwise dequant

* Clean

* Typo

* Enable tool calling

* Streamlined ux

* Add some examples

* Add docs

2025-04-29 06:23:50 -04:00

..

compat.cuh

Ensure support for cuda cc 5.3 (#960)

2024-12-01 17:46:10 -05:00

matrix_view.cuh

Implement GPTQ quantization (#467)

2024-08-09 13:49:44 -04:00

q_gemm.cu

Add the Qwen 3 and Qwen 3 MoE models! (#1285)

2025-04-29 06:23:50 -04:00

qdq_2.cuh

Implement GPTQ quantization (#467)

2024-08-09 13:49:44 -04:00

qdq_3.cuh

Implement GPTQ quantization (#467)

2024-08-09 13:49:44 -04:00

qdq_4.cuh

Implement GPTQ quantization (#467)

2024-08-09 13:49:44 -04:00

qdq_8.cuh

Implement GPTQ quantization (#467)

2024-08-09 13:49:44 -04:00

qdq_util.cuh

Implement GPTQ quantization (#467)

2024-08-09 13:49:44 -04:00