[GH-ISSUE #1018] [Bug] cant rebuild KT0.2.4 #720

New issue

Closed

opened 2026-10-29 14:43:20 +00:00 by bsakaguchi · 21 comments

bsakaguchi commented

2026-10-29 14:43:20 +00:00

Owner

Originally created by @CYSTEV-chn on GitHub (Apr 2, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1018

Checklist

1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.
3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed.
5. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-Chinese/English content without translation may be closed.

Describe the bug

i show the log, where did i make error?
i did uninstall old KT , i sure....

Reproduction

error: subprocess-exited-with-error

× Building wheel for ktransformers (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.
full command: /home/zewen/miniconda3/envs/ktransformers/bin/python /home/zewen/miniconda3/envs/ktransformers/lib/python3.11/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py build_wheel /tmp/tmp25j1mtcw
cwd: /home/zewen/ktransformers
Building wheel for ktransformers (pyproject.toml) ... error
ERROR: Failed building wheel for ktransformers
Failed to build ktransformers
ERROR: Failed to build installable wheels for some pyproject.toml based projects (ktransformers)

Environment

ubuntu 24.04
py 3.12
NVIDIA drivers 570
CUDA TOOLKIT 12.4

Originally created by @CYSTEV-chn on GitHub (Apr 2, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1018 ### Checklist - [ ] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest version. - [ ] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback. - [ ] 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed. - [ ] 5. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-Chinese/English content without translation may be closed. ### Describe the bug i show the log, where did i make error? i did uninstall old KT , i sure.... ### Reproduction error: subprocess-exited-with-error × Building wheel for ktransformers (pyproject.toml) did not run successfully. │ exit code: 1 ╰─> See above for output. note: This error originates from a subprocess, and is likely not a problem with pip. full command: /home/zewen/miniconda3/envs/ktransformers/bin/python /home/zewen/miniconda3/envs/ktransformers/lib/python3.11/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py build_wheel /tmp/tmp25j1mtcw cwd: /home/zewen/ktransformers Building wheel for ktransformers (pyproject.toml) ... error ERROR: Failed building wheel for ktransformers Failed to build ktransformers ERROR: Failed to build installable wheels for some pyproject.toml based projects (ktransformers) ### Environment ubuntu 24.04 py 3.12 NVIDIA drivers 570 CUDA TOOLKIT 12.4

bsakaguchi closed this issue

2026-10-29 14:43:20 +00:00

bsakaguchi commented

2026-10-29 14:43:20 +00:00

Author

Owner

@CYSTEV-chn commented on GitHub (Apr 2, 2025):

i solved the bug:
2. Install dependencies:
sudo apt install libtbb-dev libssl-dev libcurl4-openssl-dev libaio1 libaio-dev libfmt-dev libgflags-dev zlib1g-dev patchelf

i changed it :
sudo apt install libtbb-dev libssl-dev libcurl4-openssl-dev libaio-dev libfmt-dev libgflags-dev zlib1g-dev patchelf

then i succed.
Installation completed successfully

@CYSTEV-chn commented on GitHub (Apr 2, 2025): i solved the bug: 2. Install dependencies: sudo apt install libtbb-dev libssl-dev libcurl4-openssl-dev libaio1 libaio-dev libfmt-dev libgflags-dev zlib1g-dev patchelf i changed it : sudo apt install libtbb-dev libssl-dev libcurl4-openssl-dev libaio-dev libfmt-dev libgflags-dev zlib1g-dev patchelf then i succed. Installation completed successfully

bsakaguchi commented

2026-10-29 14:43:20 +00:00

Author

Owner

@CYSTEV-chn commented on GitHub (Apr 2, 2025):

yes! but the chat likely dont work ?
the same as Cherry studio.

@CYSTEV-chn commented on GitHub (Apr 2, 2025): yes! but the chat likely dont work ? the same as Cherry studio. ![Image](https://github.com/user-attachments/assets/a5655354-7928-4de3-b9ed-5c2676f883fd)

bsakaguchi commented

2026-10-29 14:43:20 +00:00

Author

Owner

@qiyuxinlin commented on GitHub (Apr 2, 2025):

Hello @CYSTEV-chn, can you see the three processes running through nvidia-smi, or can you paste the log of ~/.ktransformers/logs/rpc.log

@qiyuxinlin commented on GitHub (Apr 2, 2025): Hello @CYSTEV-chn, can you see the three processes running through nvidia-smi, or can you paste the log of ~/.ktransformers/logs/rpc.log

bsakaguchi commented

2026-10-29 14:43:20 +00:00

Author

Owner

@CYSTEV-chn commented on GitHub (Apr 2, 2025):

Hello @CYSTEV-chn, can you see the three processes running through nvidia-smi, or can you paste the log of ~/.ktransformers/logs/rpc.log

A new version of the following files was downloaded from https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat:

configuration_deepseek.py
. Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.
[2025-04-02 18:31:45.930] [info] [scheduler.cpp:31] Number of available GPUs: 1, want 1
[2025-04-02 18:31:45.930] [info] [scheduler.cpp:60] Each GPU Total: 549MiB, Model Params: 0MiB, KVCache: 549MiB, Left: 0MiB
[2025-04-02 18:31:45.930] [info] [scheduler.cpp:75] total_kvcache_pages is auto derived as 72
[2025-04-02 18:31:45.930] [info] [scheduler.cpp:890] Using Strategy FCFS
[2025-04-02 18:31:45.930] [info] [scheduler.cpp:442]
Scheduler Settings:
model_name: DeepSeek-V2-Lite-Chat
quant_type: BF16
model_path: deepseek-ai/DeepSeek-V2-Lite-Chat
params_count: 0
layer_count: 27
num_k_heads: 1
k_head_dim: 576
bytes_per_params: 2
bytes_per_kv_cache_element: 2
page_size: 256
gpu_device_id: 0
gpu_memory_size: 575.67M
memory_utilization_percentage: 1
max_batch_size: 4
recommended_chunk_prefill_token_count: 127
sched_metrics_port: 55863
kvc2_config_path: /home/zewen/miniconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/server/balance_serve/../../configs
kvc2_root_path: /mnt/data/persist-kvc
memory_pool_size_GB: 500
evict_count: 40
kvc2_metrics_port: 47883
load_from_disk: false
save_to_disk: true
strategy_name: FCFS
gpu_device_count: 1