HappyZ happyz
happyz synced commits to refs/pull/7542/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:08 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7531/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:07 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7527/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:07 -07:00
775425c50c Merge 4d9ed09199839b536409aa9f8a83fb0c8539a71f into d6ef0e77dd
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
4d9ed09199 disable CUDA graphs for quantized KV cache
32bc240001 fix nwarps > batch size
a62d7cb8fe add q8_0 q4_0 tests
Compare 6 commits »
happyz synced commits to refs/pull/7527/head at happyz/llama.cpp from mirror 2024-05-26 23:06:07 -07:00
4d9ed09199 disable CUDA graphs for quantized KV cache
32bc240001 fix nwarps > batch size
a62d7cb8fe add q8_0 q4_0 tests
5c7e9c4d8a fix commented-out kernel variants
Compare 4 commits »
happyz synced commits to refs/pull/7526/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:07 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7524/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:07 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7519/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:06 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
f3b5e7d436 llama : correct llm_build_moe_ffn() arguments in build_arctic()
Compare 3 commits »
happyz synced commits to refs/pull/7522/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:06 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7514/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:06 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7517/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:06 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
dff451cfa1 flake.lock: Update (#7540)
Compare 3 commits »
happyz synced commits to refs/pull/7519/head at happyz/llama.cpp from mirror 2024-05-26 23:06:06 -07:00
f3b5e7d436 llama : correct llm_build_moe_ffn() arguments in build_arctic()
happyz synced commits to refs/pull/7495/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:05 -07:00
ed7a6496ce Merge 16b3d9686242b49eb2faf4d6b9daba38827dfa8d into d6ef0e77dd
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7497/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:05 -07:00
dedc5c184c Merge 135cec29ed57beb7cacdb879c9bad9d7106d132d into d6ef0e77dd
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
dff451cfa1 flake.lock: Update (#7540)
Compare 3 commits »
happyz synced commits to refs/pull/7499/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:05 -07:00
55cfc437a5 Merge 16958a95fd71de4d8b208b4121d1bb43fb21799a into d6ef0e77dd
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
dff451cfa1 flake.lock: Update (#7540)
d298382ad9 main: replace --no-special with --special (#7534)
32a28217f4 Fix aya-23 conversion scripts (#7539)
Compare 5 commits »
happyz synced commits to refs/pull/7504/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:05 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
dff451cfa1 flake.lock: Update (#7540)
d298382ad9 main: replace --no-special with --special (#7534)
32a28217f4 Fix aya-23 conversion scripts (#7539)
Compare 5 commits »
happyz synced commits to refs/pull/7481/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:04 -07:00
1101640b3d Merge 5b2ef0d0aff8059f5d642f8892a3cae67c2db81d into d6ef0e77dd
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 2 commits »
happyz synced commits to refs/pull/7477/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:04 -07:00
879ed61d03 Merge 74716945ff66f2a8b437bac69367aced99099e06 into d6ef0e77dd
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
dff451cfa1 flake.lock: Update (#7540)
d298382ad9 main: replace --no-special with --special (#7534)
32a28217f4 Fix aya-23 conversion scripts (#7539)
Compare 6 commits »
happyz synced commits to refs/pull/7487/head at happyz/llama.cpp from mirror 2024-05-26 23:06:04 -07:00
0adedd712e move unsed variable
c812542f86 better toolchain compability
9a166331e0 use larger block size
3047229758 basic implementation
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
Compare 37 commits »
happyz synced commits to refs/pull/7487/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:04 -07:00
0adedd712e move unsed variable
c812542f86 better toolchain compability
9a166331e0 use larger block size
3047229758 basic implementation
Compare 6 commits »
happyz synced commits to refs/pull/7488/merge at happyz/llama.cpp from mirror 2024-05-26 23:06:04 -07:00
d6ef0e77dd github: add self sorted issue ticket forms (#7543)
dff451cfa1 flake.lock: Update (#7540)
Compare 3 commits »