jtang613

Tested on two of my CPE's requiring it. Works on both.

It looks like LimeSuite is connected to your LimeSDR, causing contention when SRSRAN is trying to claim the SDR interface. Or possibly it is mistakenly detecting LimeRFE as a LimeSDR...

See https://github.com/srsran/srsRAN/blob/f2dff0b7a03e065060b48ea0a3c7a6a7890dfd46/srsenb/src/enb_cfg_parser.cc#L1834 for a list of DL_ARFCN's that are enabled.

Looks like a problem with your UHD (USRP). Could be a number of causes: * Heisenbug: unplug the USRP and then plug it back in. * permission issue: try running...

The startup log has the clue: ``` Soapy has found device #0: default_input=True, default_output=True, device_id=0, driver=audio, label=hw:HDA Intel,0, Soapy has found device #1: default_input=False, default_output=False, device_id=1, driver=audio, label=default, Soapy has...

This appears to be the same issue as in https://github.com/srsran/srsRAN/issues/770 and https://github.com/srsran/srsRAN/issues/803 I'd consider this to now be a verified issue. Issue 770 has a code snippet that claims to...

Your RX gain is likely too low. I've found values of around 75 to work best on LimeSDR-USB. Alternatively, commenting out the rx_gain line to allow the AGC to adjust...

llama.cpp is an interesting development - supports Mac M1/M2 and x86 AVX2 instructions (ie: it's pretty quick for a CPU implementation). I'm able to load the 65B-4bit and get around...

The 7B will run on a single GPU, but the other models *require* multiple. The LLaMA sample code also really wants a lot of VRAM (16GB seems to be bare...

I'm seeing good results from LLaMA 7B. It seems to produce results comparable to OPT-30b, but noticeably quicker. I've also tried the llama-int8 fork and while it does work, I'm...