kaizau

@ltrung We're trying to use a priority-based downlink policy to implement a featured view, but so far, haven't been able achieve a satisfactory result. The goal is to have a...

@vidya-mohan @ltrung Yes, thank you. This generally pointed me in the right direction. Simulcast felt like overkill in our use case, so we ended up using `setHasBandwidthPriority` on the default...

Also experiencing this exact issue. In my case, the problem is immediately preceded by all the renditions becoming blacklisted. I'm logging this out like so: ``` player.tech().on("usage", e => {...

Re: https://github.com/ggerganov/llama.cpp/issues/6726#issuecomment-2065729990 > @ngxson The main problem is that even with this level of flexibility, some templates can't be supported without doing some code logic (for example, llama 2 template...

Re: https://github.com/ggerganov/llama.cpp/issues/6726#issuecomment-2065440493 > @bullno1 Sounds cool and i'd say take it further, why even template or search&replace within a role? Just change it to "prefix" and "suffix": Might just be...

@teleprint-me Seems like chat templates brushes up against a macro question around the ideal scope of llama.cpp and this server "example" in general. But whether the `chat` endpoint is here...

I haven't had the chance to test, but try .5px for the adjustment. On Jan 7, 2012, at 1:20 PM, Dane O'[email protected] wrote: > With the current API it's difficult...

Thanks for the note — I'll look into it.

Hm, seems to be working fine on the latest Mac version. Could you provide more details? 

Sadly, I don't have my Ubuntu box while traveling. Could you post a screenshot with the console error log, or anything else that might be relevant?