vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-05 12:09:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2
764 commits 40 branches 19 tags 46 MiB
Commit graph

26 commits

Author SHA1 Message Date
qiyuxinlin
c6aa379de2 support safetensor load, delete architectures argument 2025-05-09 10:38:29 +00:00
qiyuxinlin
27990dc6fb fix load bug 2025-04-28 21:08:13 +00:00
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
root
921061666c fix some bugs 2025-04-17 00:48:09 +08:00
Atream
25cee5810e add balance-serve, support concurrence 2025-03-31 22:55:32 +08:00
Atream
6f43bbe55f fix-singleton 2025-03-14 04:16:53 +00:00
liam
ffb86c66e3 ⚡ fix experts torch 2025-02-26 15:04:40 +08:00
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
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
e8e02e5ccc support Moonlight 2025-02-23 14:21:18 +00:00
DDong Jianwei
95d937c51d tmp 2025-02-23 18:51:42 +08:00
Atream
038bc30888 fix precision bug imported by position_ids in 0.2.0 2025-02-17 09:23:14 +00:00
Atream
c189d55bd1 toy support for experts on GPU, no CUDA Graph 2025-02-15 15:16:00 +00:00
Azure
c4d9bc6670 support KExpertsMarlin backend 2025-02-07 05:57:40 +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
xhedit
234faf7987 typo fix: KMisrtal -> KMistral 2024-09-12 15:58:01 +00:00
TangJingqi
6735beb5b6 Fix cannot offload whole layer in cpu 2024-08-29 19:10:14 +08:00
chenxl
4d1d561d28 [feature] release 0.1.3 2024-08-28 16:11:43 +00:00
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
chenht2022
c1cc7d2cd2 1) Linear and MLP operators support qlen>1; 2) All operators now share a single memory buffer; 3) Refactor CPUInfer submit/sync logic. 2024-08-08 09:04:36 +00:00
chenxl
18c42e67df Initial commit 2024-07-27 16:06:58 +08:00