FFAMax
FFAMax
Hi Team. What do you think about rules support? I found significant benefit of using rules instead of dictionaries in cases of 8-9 symbols numbers. - This approach reduce overhead...
_**Have to verify on prod data!**_ Verification: ``` function get_essid_original($net) { if ($net['keyver'] == 100) { $apmkid = explode('*', $net['struct'], 4); return hex2bin($apmkid[3]); } else { $essid_len = ord(substr($net['struct'], 0x09,...
# go get github.com/vlad-s/hcpxread # golang.org/x/sys/unix go/src/golang.org/x/sys/unix/syscall.go:83:16: undefined: unsafe.Slice go/src/golang.org/x/sys/unix/syscall_linux.go:2270:9: undefined: unsafe.Slice go/src/golang.org/x/sys/unix/syscall_unix.go:118:7: undefined: unsafe.Slice go/src/golang.org/x/sys/unix/sysvshm_unix.go:33:7: undefined: unsafe.Slice
Found for now it will pick first shown by `nvidia-smi`
``` raceback (most recent call last): File "/home/ffamax/exo/exo/api/chatgpt_api.py", line 273, in handle_post_chat_completions await asyncio.wait_for(self.node.process_prompt(shard, prompt, image_str, request_id=request_id), timeout=self.response_timeout) File "/home/ffamax/miniconda3/envs/.venv.py3.12/lib/python3.12/asyncio/tasks.py", line 520, in wait_for return await fut ^^^^^^^^^ File "/home/ffamax/exo/exo/orchestration/standard_node.py",...
Found this module was missed by requirements. Need to install manually: ``` pip install llvmlite ```
Hello, Team. Trying following manual to have env installed on Debian, seems like something else required, getting: ``` /usr/local/cuda/include/cuda.h: No such file or directory root@b250:~/cudnn_samples_v9/mnistCUDNN# make clean && make rm...
https://github.com/exo-explore/exo/blob/bc1d88d86d6a016669974d7d3dbf87fc07b18bc7/exo/helpers.py#L38 If user A used exo, user B will unable to use exo due tmp file blocked by user A until manually removed or system reloaded (in cases tmp folder...
Tmp folder permission may mislead root cause showing issue with binding socket ``` Detected system: Linux Inference engine name after selection: tinygrad get_inference_engine called with: tinygrad Using inference engine: TinygradDynamicShardInferenceEngine...
Immediately after restart host may switch from GPU/CUDE device to CLANG and nothing can do except shutdown other peers to find who causing the issue. On unhealthy host issue detected...