llama_cpp

9,079 Commits 1 Branch 0 Tags

2 Commits

Author	SHA1	Message	Date
PikaPikachuandGitHub	9db77a020c	model : refactor QKV into common build_qkv and create_tensor_qkv helpers (#21245 ) * model : refactor QKV into common build_qkv and create_tensor_qkv helpers * model : extend build_qkv to bert/mpt/dbrx/olmo/lfm2/nemotron-h/granite-hybrid/gemma3n-iswa/t5-dec and fix wqkv_s	2026-04-16 17:41:34 +02:00
PikaPikachuandGitHub	617db241aa	cuda : add RDNA4-specific MMVQ parameter table for bs=1 decode (#19478 ) * mmvq: add RDNA3/RDNA4-specific parameter table (nwarps=8, rows=1) * mmvq: add dedicated RDNA3 parameter table * mmvq: exclude RDNA3.5 (gfx1150/1151) from RDNA3 table	2026-03-15 08:33:39 +01:00

Author

SHA1

Message

Date

PikaPikachuandGitHub

9db77a020c

model : refactor QKV into common build_qkv and create_tensor_qkv helpers (#21245 )

* model : refactor QKV into common build_qkv and create_tensor_qkv helpers

* model : extend build_qkv to bert/mpt/dbrx/olmo/lfm2/nemotron-h/granite-hybrid/gemma3n-iswa/t5-dec and fix wqkv_s

2026-04-16 17:41:34 +02:00

PikaPikachuandGitHub

617db241aa

cuda : add RDNA4-specific MMVQ parameter table for bs=1 decode (#19478 )

* mmvq: add RDNA3/RDNA4-specific parameter table (nwarps=8, rows=1)

* mmvq: add dedicated RDNA3 parameter table

* mmvq: exclude RDNA3.5 (gfx1150/1151) from RDNA3 table

2026-03-15 08:33:39 +01:00