Jesse Gross 0bda72892c llm: Enable flash attention by default for qwen3 and qwen3moe

2025-10-02 17:04:10 -07:00

..

ggml_test.go

ggml: fix crash for array head counts

2025-04-27 11:38:06 -07:00

ggml.go

llm: Enable flash attention by default for qwen3 and qwen3moe

2025-10-02 17:04:10 -07:00

gguf_test.go

convert: fix tensor sorting (#12015)

2025-08-26 13:57:46 -07:00

gguf.go

convert: fix tensor sorting (#12015)

2025-08-26 13:57:46 -07:00

type.go

convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)

2025-08-26 16:41:02 -07:00