issues
search
kvcache-ai
/
ktransformers
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Apache License 2.0
641
stars
31
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Installation requirements
#89
arthurv
opened
1 day ago
1
[fix] Fix some gpu dequant function doesn't support multi gpu bug
#88
Azure-Tang
opened
1 day ago
0
are marline and q4k totally equivalent?
#87
Eutenacity
opened
1 day ago
1
typo fix: KMisrtal -> KMistral
#86
xhedit
opened
2 days ago
0
Getting reasonable performance on dual RTX 3090 and 128gb
#85
myfrienderic
opened
3 days ago
5
可以给出详细的硬件配置清单吗?
#84
qixing-ai
opened
3 days ago
2
Use cond var to avoid busy loop
#83
sayap
opened
3 days ago
1
Seg Fault on long replies
#82
matthusby
closed
3 days ago
2
Fix backend
#81
chenht2022
closed
3 days ago
0
Busy loop in cpu_backend/task_queue.cpp keeps 1 thread at 100% CPU when queue is empty
#80
sayap
opened
5 days ago
5
Is deepseek-ai/DeepSeek-V2.5 supported?
#79
AshD
closed
4 days ago
9
Fix: Wrong type of token list returned by prefill_and_generate
#77
TKONIY
opened
1 week ago
0
8-GPU configuration on L40 OOM
#76
fengyang95
closed
3 days ago
8
How can i run internlm2_5-7b-chat-1m in ktransformers?
#74
Ma1oneZhang
closed
5 days ago
4
When the input token exceeds 4096, an error will occur.
#73
fengyang95
closed
1 week ago
4
Support IQ4_XS dequantize
#72
sayap
closed
1 week ago
4
[fix] Fix qlen > chunk_size mask is none error
#71
Azure-Tang
closed
1 week ago
0
UnboundLocalError: cannot access local variable 'chunck_mask' where it is not associated with a value
#70
fengyang95
closed
1 week ago
2
Missing pip packages flash_attn and wheel
#69
bitbottrap
closed
1 week ago
2
What is the maximum input token size supported for DeepSeek V2?
#68
fengyang95
closed
3 days ago
1
[fix] fix bugs about Qwen2-57B, install requirement, DockerFile
#67
UnicornChan
closed
2 weeks ago
0
docker container fails to start due to missing package 'uvicorn'
#66
sammcj
closed
4 days ago
1
Would you support glm4-chat-1m
#65
choyakawa
opened
2 weeks ago
1
docs: update long_context_introduction.md
#64
eltociear
closed
2 weeks ago
0
[Fix] Fix problem that ktransformers cannot offload whole layer in cpu
#62
Azure-Tang
closed
2 weeks ago
0
docker builds and pip install broken - No module named 'cpufeature'
#61
sammcj
closed
2 weeks ago
5
fix(docs): fix broken link
#60
sammcj
closed
2 weeks ago
0
[fix] Fix readme datas
#58
Azure-Tang
closed
2 weeks ago
0
[feature] release 0.1.3
#57
UnicornChan
closed
2 weeks ago
0
Update README.md
#56
hyx1999
closed
2 weeks ago
0
Add a instruction for configuring CUDA_HOME and CUDA_PATH to the install section of README.md.
#54
hyx1999
closed
2 weeks ago
2
Support for Mistral-Large-Instruct-2407-GGUF ?
#53
LIUKAI0815
closed
2 weeks ago
2
Fix: None for load config
#52
UnicornChan
closed
3 weeks ago
0
[fix] f16 dequantize device ignored
#51
molamooo
closed
3 weeks ago
0
How to properly disable offloading MoE layers to CPU?
#50
molamooo
closed
2 weeks ago
5
More Efficient Layer Distribution for DeepSeek Coder v2 on Multiple GPUs and CPUs
#49
BGFGB
opened
3 weeks ago
4
[fix] Fix bugs about static cache and server param;
#48
Azure-Tang
closed
3 weeks ago
0
Can I run llama3.1 70b with rtx4090+64g ddr5 ram?
#47
codeMonkey-shin
opened
3 weeks ago
1
[ENHANCEMENT] improve GPU utilization for multi-GPU
#46
ELigoP
closed
3 weeks ago
1
Cannot run DeepSeek V2 Chat in server mode on 2 GPUs
#45
ELigoP
closed
3 weeks ago
1
CUDA error: No kernel image is available for execution on the device
#44
Forsworns
closed
3 weeks ago
2
Update install.sh
#43
RealLittleXian
closed
3 weeks ago
4
Mixtral-8x7B-v0.1 GGUF file error
#42
RealLittleXian
closed
3 weeks ago
1
[Update] Update README
#41
Azure-Tang
closed
4 weeks ago
0
[fix] fix broken link
#40
Azure-Tang
closed
4 weeks ago
0
[fix] fix broken link
#39
Azure-Tang
closed
4 weeks ago
0
[update] README
#38
Azure-Tang
closed
1 month ago
0
Ubuntu 24.04 GLIBCXX version fail
#37
ELigoP
closed
3 weeks ago
3
Release v0.1.2
#36
UnicornChan
closed
1 month ago
0
[update] Update readme; Add tutorial
#35
Azure-Tang
closed
1 month ago
0
Next