refactor: unify rotary embedding interface and update docs

- Merge cos/sin into single freqs_cis tensor [batch, seq, dim/2, 2] throughout the pipeline: RotaryEmbedding buffer, forward return type, apply_rotary_emb signature, CUDA kernel interface
- CUDA kernel now takes freqs_cis directly and reads cos/sin via stride offset internally, eliminating Python-side slice/copy overhead
- Kernel interface: rotary_emb(x, freqs_cis) replaces rotary_emb(x, cos, sin)
- All call sites pass rotary_emb as Tensor (was tuple), type annotations consistent
- Update build threads from 8 to 16
- Fix all docs: get-started, inference, training, cuda_kernels, architecture, internals — reflect new rotary interface, KVCache fields, rotary backend dispatch, .so path, kernel registry count, file layout

This commit is contained in:

ViperEkura

2026-07-31 16:52:25 +08:00

parent 75411ce0cc

commit 7aa5ed09d9

11 changed files with 120 additions and 83 deletions

									
										csrc/build.py
									
		+1
		-1
	
												View File
												
				@@ -53,7 +53,7 @@ NVCC_FLAGS = [

				    "--use_fast_math",

				    "--ptxas-options=-O3,-v",

				    "--extra-device-vectorization",

				    "--threads=8",

				    "--threads=16",

				]