HappyZ happyz
happyz synced commits to refs/pull/6602/head at happyz/llama.cpp from mirror 2024-05-10 06:38:42 -07:00
f63f147471 Merge branch 'master' into new_minicpm
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 155 commits »
happyz synced commits to refs/pull/6522/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:42 -07:00
a51023b375 Merge 62e98ad17977339ebf634d443f0490e820c66340 into 4e3880978f
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
62e98ad179 Merge branch 'master' into amd-warp-reduce
Compare 17 commits »
happyz synced commits to refs/pull/6522/head at happyz/llama.cpp from mirror 2024-05-10 06:38:42 -07:00
62e98ad179 Merge branch 'master' into amd-warp-reduce
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 218 commits »
happyz synced commits to refs/pull/6440/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:41 -07:00
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
160d0f0a8b Merge branch 'master' into master
Compare 125 commits »
happyz synced commits to refs/pull/6467/head at happyz/llama.cpp from mirror 2024-05-10 06:38:41 -07:00
e56761dc74 Merge branch 'master' into feature_grammar_char_any
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 237 commits »
happyz synced commits to refs/pull/6454/head at happyz/llama.cpp from mirror 2024-05-10 06:38:41 -07:00
2cb9174c67 Merge branch 'master' into master
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 251 commits »
happyz synced commits to refs/pull/6445/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:41 -07:00
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
68e7c2579a Merge branch 'master' into smooth-pr
Compare 125 commits »
happyz synced commits to refs/pull/6445/head at happyz/llama.cpp from mirror 2024-05-10 06:38:41 -07:00
68e7c2579a Merge branch 'master' into smooth-pr
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 252 commits »
happyz synced commits to refs/pull/6454/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:41 -07:00
ea5176f75a Merge 2cb9174c6728abd00fd78688b8ff34b3d3b9b074 into d11afd6652
d11afd6652 llava : fix moondream support (#7163)
2cb9174c67 Merge branch 'master' into master
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
Compare 157 commits »
happyz synced commits to refs/pull/6403/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:40 -07:00
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
Compare 18 commits »
happyz synced commits to refs/pull/6413/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:40 -07:00
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 10 commits »
happyz synced commits to refs/pull/6358/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:40 -07:00
d11afd6652 llava : fix moondream support (#7163)
e70fba507d Merge branch 'master' into master
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
Compare 70 commits »
happyz synced commits to refs/pull/6440/head at happyz/llama.cpp from mirror 2024-05-10 06:38:40 -07:00
160d0f0a8b Merge branch 'master' into master
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 428 commits »
happyz synced commits to refs/pull/6312/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:39 -07:00
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
Compare 3 commits »
happyz synced commits to refs/pull/6358/head at happyz/llama.cpp from mirror 2024-05-10 06:38:39 -07:00
e70fba507d Merge branch 'master' into master
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 283 commits »
happyz synced commits to refs/pull/6310/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:39 -07:00
e4ac8ae720 Update llama.h respect current numerology
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
Compare 37 commits »
happyz synced commits to refs/pull/6310/head at happyz/llama.cpp from mirror 2024-05-10 06:38:39 -07:00
e4ac8ae720 Update llama.h respect current numerology
3a8387863f Merge branch 'master' into Nexesenex-IQ1_XS-IQ1_S-quant-strategies
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
Compare 298 commits »
happyz synced commits to refs/pull/4858/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:38 -07:00
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
Compare 7 commits »
happyz synced commits to refs/pull/6188/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:38 -07:00
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
Compare 3 commits »
happyz synced commits to refs/pull/6035/head at happyz/llama.cpp from mirror 2024-05-10 06:38:38 -07:00
5430a305be add get rows for q8_0 with out view