45 commits

Author	SHA1	Message	Date
djw	3f9bbf1181	support qwen3, dont speak human language	2025-04-28 08:44:47 +00:00
chenht2022	f3d842a0ca	support AMX	2025-04-25 14:47:16 +00:00
Azure-Tang	203b853c75	rm KMoEGateDeepSeekV3, fall back to KMoEGate	2025-04-01 07:13:05 +00:00
Atream	25cee5810e	add balance-serve, support concurrence	2025-03-31 22:55:32 +08:00
Azure-Tang	85c32fdd10	Fix rocm example yaml	2025-03-15 22:27:02 -04:00
Azure	3986e2d2cf	Merge pull request #178 from fxzjshm/hip ... [Feat] Port to ROCm/HIP	2025-03-15 02:31:07 +08:00
Azure-Tang	e5b001d76f	Update readme; Format code; Add example yaml.	2025-03-14 14:25:52 -04:00
Atream	a889288fc1	use compile for gate, slight performance improvement	2025-03-14 12:43:28 +00:00
Azure-Tang	ed8437413b	merge main; Add torch q8 linear	2025-03-14 05:52:07 -04:00
Atream	90eb87b3fc	Update DeepSeek-V3-Chat-multi-gpu-marlin.yaml	2025-02-26 21:53:50 +08:00
Azure	91c1619296	Merge branch 'develop-0.2.2' into support-fp8 ... Update README.md	2025-02-25 13:43:26 +00:00
Azure	2c0cce90d0	add fp8 multi gpu yaml example	2025-02-25 13:32:09 +00:00
Atream	477ac28a9c	fix-update-flashinfer_wrapper_local_chat	2025-02-25 12:47:31 +00:00
Atream	b443c7dfa2	Merge pull request #657 from kvcache-ai/feat-absorb-for-long-prefill ... Feat absorb for long prefill	2025-02-25 16:53:21 +08:00
Atream	f4c198bd42	support absorb for prefill long context	2025-02-25 08:52:02 +00:00
Azure	ca7366d2db	Merge remote-tracking branch 'upstream/develop-0.2.2' into support-fp8	2025-02-24 11:58:10 +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	f327695079	fix KExpertsMarlin on GPU with out CUDA Graph	2025-02-24 09:30:54 +00:00
Atream	f5f6c6b95d	update yaml	2025-02-23 14:33:58 +00:00
DDong Jianwei	95d937c51d	tmp	2025-02-23 18:51:42 +08:00
Atream	5ec33d046d	optimize gguf dequant, save mem, support Q2_K ... use marlin for lm_head, lm_head only calc last token for prefill extend context window to 19K for DeepSeek-V3/R1 within 24GB VRAM	2025-02-22 06:13:01 +00:00
Atream	7e1fe256c8	optimize GPU	2025-02-21 05:06:57 +00:00
Atream	c189d55bd1	toy support for experts on GPU, no CUDA Graph	2025-02-15 15:16:00 +00:00
Azure	b7653b9c4f	add V3/R1 8 gpu yaml example	2025-02-14 02:56:13 +00:00
MorphisZhang	aea4243712	Add optimization config for Deepseek V3/R1 with 4 GPUs	2025-02-13 16:32:28 +08:00
Azure	0564ac8465	update marlin expert example	2025-02-12 04:11:00 +00:00
liam	83401dbb3b	⚡ ready to publish	2025-02-10 12:29:23 +08:00
Azure	c4d9bc6670	support KExpertsMarlin backend	2025-02-07 05:57:40 +00:00
Azure	ee24a27001	update v3 single gpu rule yaml;	2025-02-04 16:14:35 +00:00
Azure	907251c743	done support deepseekv3	2025-02-04 15:53:38 +00:00
Azure	f748cd29f0	fix rope; update moegate	2025-02-01 18:05:45 +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
anyanqilin	2d67016d14	wjh-change	2024-11-04 14:02:19 +08:00
xhedit	234faf7987	typo fix: KMisrtal -> KMistral	2024-09-12 15:58:01 +00:00
chenxl	49cce0c437	[fix] bugs about Qwen57B, install requirement, Dockerfile	2024-08-30 09:51:32 +00:00
TangJingqi	8747c099f2	update yaml example; update version idx; update docker file	2024-08-29 22:39:20 +08:00
TangJingqi	abd4214b56	fix readme; adjust param	2024-08-29 10:40:08 +08:00
chenxl	4d1d561d28	[feature] release 0.1.3	2024-08-28 16:11:43 +00:00
TangJingqi	de3faaf55d	Update readme; add pipeline tutorial; add detailed inject tutorial	2024-08-15 20:42:54 +08:00
TangJingqi	c47205dce9	fix name	2024-08-15 11:25:12 +08:00
TangJingqi	67043b4b5c	[fix] format classes and files name	2024-08-15 10:44:59 +08:00
Atream	412055d450	[feature] experts can be injected using CPUInfer ... [fix] fix ktransformers interface when use new CUDAGraphRunner [fix] fix YAML and optimize logic, the top rule has the highest priority	2024-08-14 16:10:54 +08:00
chenxl	f5f79f5c0e	[ADD] support multi-gpu qlen>1 q5_k	2024-08-12 11:41:26 +00:00
chenxl	18c42e67df	Initial commit	2024-07-27 16:06:58 +08:00