14 commits

Author	SHA1	Message	Date
djw	3f9bbf1181	support qwen3, dont speak human language	2025-04-28 08:44:47 +00:00
Azure-Tang	203b853c75	rm KMoEGateDeepSeekV3, fall back to KMoEGate	2025-04-01 07:13:05 +00:00
Azure-Tang	3a5330b215	Merge branch 'main' into work-concurrent	2025-04-01 06:48:19 +00:00
Atream	25cee5810e	add balance-serve, support concurrence	2025-03-31 22:55:32 +08:00
Atream	633af5d235	Update gate.py	2025-03-20 14:54:01 +08:00
Atream	b453333f60	Update gate.py	2025-03-19 16:14:54 +08:00
Atream	44599229cd	Update gate.py	2025-03-19 12:16:48 +08:00
Atream	114995355b	fix-gate-compile	2025-03-19 11:27:18 +08:00
Atream	a889288fc1	use compile for gate, slight performance improvement	2025-03-14 12:43:28 +00:00
Azure	581a524f65	Add data loader to read special weights for fp8; Add special weight process script	2025-02-24 11:34:17 +00:00
Atream	038bc30888	fix precision bug imported by position_ids in 0.2.0	2025-02-17 09:23:14 +00:00
Azure	907251c743	done support deepseekv3	2025-02-04 15:53:38 +00:00
Azure	f873558a89	update rope calculation; update modeling.py; update gate for moe	2025-02-01 07:32:21 +00:00
Azure	476b1d8dc6	support deepseekv3; runable but have precition problem	2025-01-31 08:27:24 +00:00