Atream f35e8d41d8 support chunk prefill, support 139K context for 24G VRAM		2025-03-01 11:28:25 +00:00
..
cuda_graph_runner.py	[feature] release 0.1.3	2024-08-28 16:11:43 +00:00
custom_gguf.py	Fix RuntimeError on Windows caused by integer overflow in np.prod	2025-02-26 03:50:12 +08:00
custom_loader.py	Add data loader to read special weights for fp8; Add special weight process script	2025-02-24 11:34:17 +00:00
modeling_rope_utils.py	update rope calculation; update modeling.py; update gate for moe	2025-02-01 07:32:21 +00:00
textstream.py	Initial commit	2024-07-27 16:06:58 +08:00
utils.py	support chunk prefill, support 139K context for 24G VRAM	2025-03-01 11:28:25 +00:00