Inference › Inference Engines
llama.cpp / GGUF

Users browsing this forum: 4 Guest(s)
Mark this forum read
llama.cpp / GGUF
Thread / Author Replies Views Rating Last Post [asc]
   
Go to first unread post context size vs speed in GGUF: worth it? (Pages: 1 2 )
visionyard23, 10-18-2026, 03:30 PM
 15 353
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 05:58 AM
Last Post: macroforge
    15 344
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 05:46 AM
Last Post: bytesupply76
    8 203
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 05:46 AM
Last Post: mintstream9
   
Go to first unread post speculative decoding in llama.cpp (Pages: 1 2 )
vrambandit, 10-13-2026, 12:19 AM
 13 308
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 05:36 AM
Last Post: bytesupply76
   
Go to first unread post speculative decoding in llama.cpp (Pages: 1 2 )
phasetrack, 10-16-2026, 10:05 PM
 11 294
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 05:20 AM
Last Post: visionyard23
   
Go to first unread post speculative decoding in llama.cpp (Pages: 1 2 )
bytesupply76, 10-17-2026, 10:08 AM
 15 329
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 04:52 AM
Last Post: mangotinker73
   
Go to first unread post context size vs speed in GGUF with vLLM (Pages: 1 2 )
embershed99, 10-12-2026, 01:53 AM
 13 271
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 04:06 AM
Last Post: phasescope
   
Go to first unread post prefix caching in llama.cpp (Pages: 1 2 )
vectorport, 10-17-2026, 02:04 PM
 12 307
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 04:03 AM
Last Post: latentcraft
    15 373
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 02:30 AM
Last Post: mangotinker73
   
Go to first unread post prefix caching in llama.cpp: worth it? (Pages: 1 2 )
northcraft90, 10-14-2026, 10:53 PM
 15 339
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 01:25 AM
Last Post: visionyard23
    6 213
  • 0 Vote(s) - 0 out of 5 in Average
 10-19-2026, 12:32 AM
Last Post: mangotinker73
    13 272
  • 0 Vote(s) - 0 out of 5 in Average
 10-18-2026, 10:32 PM
Last Post: pixelcrate82
    8 230
  • 0 Vote(s) - 0 out of 5 in Average
 10-18-2026, 09:12 PM
Last Post: visionyard23
   
Go to first unread post multi-GPU offload advice
bytesupply76, 10-18-2026, 01:20 PM
 0 78
  • 0 Vote(s) - 0 out of 5 in Average
 10-18-2026, 01:20 PM
Last Post: bytesupply76
    2 127
  • 0 Vote(s) - 0 out of 5 in Average
 10-17-2026, 12:35 PM
Last Post: vrambandit
   
Go to first unread post prefix caching in llama.cpp for Phi (Pages: 1 2 )
mangoquill, 10-07-2026, 04:06 AM
 14 303
  • 0 Vote(s) - 0 out of 5 in Average
 10-16-2026, 06:52 PM
Last Post: mellowwire98
    6 176
  • 0 Vote(s) - 0 out of 5 in Average
 10-16-2026, 09:03 AM
Last Post: vrambandit
   
Go to first unread post speculative decoding in llama.cpp (Pages: 1 2 )
bytesupply76, 10-09-2026, 10:02 PM
 14 322
  • 0 Vote(s) - 0 out of 5 in Average
 10-15-2026, 08:11 PM
Last Post: northcraft90
   
Go to first unread post prefix caching in llama.cpp with PyTorch (Pages: 1 2 )
vrambandit, 10-06-2026, 10:18 AM
 12 285
  • 0 Vote(s) - 0 out of 5 in Average
 10-14-2026, 10:23 PM
Last Post: bytesupply76
    1 104
  • 0 Vote(s) - 0 out of 5 in Average
 10-14-2026, 09:21 PM
Last Post: thetagrid15


  New Posts
  Hot Thread (New)
  Hot Thread (No New)
  No New Posts
  Contains Posts by You
  Closed Thread

Search this Forum:

Forum Jump: