- 04 Nov, 2024 7 commits
-
-
liam authored
-
liam authored
-
anyanqilin authored
-
anyanqilin authored
-
anyanqilin authored
-
liam authored
-
liam authored
-
- 09 Oct, 2024 4 commits
-
-
Chen Hongtao authored
Adapt Windows
-
chenht2022 authored
-
UnicornChan authored
Fix: Wrong type of token list returned by prefill_and_generate
-
Chen Hongtao authored
Use cond var to avoid busy loop
-
- 19 Sep, 2024 1 commit
-
-
UnicornChan authored
typo fix: KMisrtal -> KMistral
-
- 15 Sep, 2024 1 commit
-
-
UnicornChan authored
[fix] Fix some gpu dequant function doesn't support multi gpu bug
-
- 13 Sep, 2024 2 commits
- 12 Sep, 2024 1 commit
-
-
xhedit authored
-
- 11 Sep, 2024 1 commit
-
-
Yap Sok Ann authored
-
- 06 Sep, 2024 1 commit
-
-
UnicornChan authored
Support IQ4_XS dequantize
-
- 05 Sep, 2024 1 commit
-
-
yangshen authored
-
- 02 Sep, 2024 3 commits
-
-
UnicornChan authored
[fix] Fix qlen > chunk_size mask is none error
-
Azure authored
-
Yap Sok Ann authored
-
- 30 Aug, 2024 3 commits
-
-
UnicornChan authored
[fix] fix bugs about Qwen2-57B, install requirement, DockerFile
-
chenxl authored
-
UnicornChan authored
docs: update long_context_introduction.md
-
- 29 Aug, 2024 10 commits
-
-
chenxl authored
-
Ikko Eltociear Ashimine authored
accuary -> accuracy
-
UnicornChan authored
[Fix] Fix problem that ktransformers cannot offload whole layer in cpu
-
TangJingqi authored
-
TangJingqi authored
-
Atream authored
fix(docs): fix broken link
-
Sam authored
-
Azure authored
[fix] Fix readme datas
-
TangJingqi authored
-
TangJingqi authored
-
- 28 Aug, 2024 4 commits
-
-
UnicornChan authored
[feature] release 0.1.3
-
chenxl authored
-
UnicornChan authored
Update README.md
-
_HYX_ authored
Set the reminder to set CUDA_HOME and CUDA_PATH in the README to the "Quick Start" section under "Install CUDA".
-
- 22 Aug, 2024 1 commit
-
-
UnicornChan authored
Fix: None for load config
-
