HappyZ happyz
happyz synced commits to refs/pull/6919/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -07:00
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)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/6951/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -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 7 commits »
happyz synced commits to refs/pull/6958/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -07:00
51251f54be Merge 339b2a51509497d225ec03e30392e4f203c81b46 into d11afd6652
d11afd6652 llava : fix moondream support (#7163)
Compare 2 commits »
happyz synced commits to refs/pull/6942/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -07:00
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)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/6934/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -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/6866/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:46 -07:00
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
d12c57b559 Update convert-hf-to-gguf.py
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
Compare 6 commits »
happyz synced commits to refs/pull/6915/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:46 -07:00
b63674635d Merge e2dcf468dc40866ff4468bdc0b41d61bbaf5caec into 25c6e82e7a
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)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/6892/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:46 -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)
Compare 4 commits »
happyz synced commits to refs/pull/6869/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:46 -07:00
40b55af48b Merge cf9dca34cbd02c89fb3f3c46e85da817fe89744b 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)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
Compare 6 commits »
happyz synced commits to refs/pull/6834/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:45 -07:00
abb406b888 Merge branch 'master' into hkvc_chaton_v3
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
Compare 24 commits »
happyz synced commits to refs/pull/6844/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:45 -07:00
d11afd6652 llava : fix moondream support (#7163)
Compare 2 commits »
happyz synced commits to refs/pull/6834/head at happyz/llama.cpp from mirror 2024-05-10 06:38:45 -07:00
abb406b888 Merge branch 'master' into hkvc_chaton_v3
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 44 commits »
happyz synced commits to refs/pull/6839/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:45 -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)
Compare 4 commits »
happyz synced commits to refs/pull/6866/head at happyz/llama.cpp from mirror 2024-05-10 06:38:45 -07:00
d12c57b559 Update convert-hf-to-gguf.py
happyz synced commits to refs/pull/6828/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:44 -07:00
bffcd7b185 Merge 48e569901ff7543fdb6e9f8dc633f4a36a2b7933 into 25c6e82e7a
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)
d11afd6652 llava : fix moondream support (#7163)
Compare 6 commits »
happyz synced commits to refs/pull/6826/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:44 -07:00
397b1f8f9d vulkan : add dev notes
536983b1ad ggml : fix assert message
a1278f13da minor : clean-up
d9adb8832b Merge remote-tracking branch 'origin/gg/refactor-alibi-2' into HEAD
Compare 14 commits »
happyz synced commits to refs/pull/6829/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:44 -07:00
bc394a1dfd Merge 81aeb1c68e0d4c05e1b1df9fab34ac15c76da014 into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
81aeb1c68e readme : trim trailing whitespace
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
Compare 21 commits »
happyz synced commits to refs/pull/6829/head at happyz/llama.cpp from mirror 2024-05-10 06:38:44 -07:00
81aeb1c68e readme : trim trailing whitespace
c95e54cf6f add README
1c4c975430 win32 support
21b67645c0 fix warning
5253963d73 add get_device_memory
Compare 54 commits »
happyz synced commits to refs/pull/6826/head at happyz/llama.cpp from mirror 2024-05-10 06:38:44 -07:00
a1278f13da minor : clean-up
d9adb8832b Merge remote-tracking branch 'origin/gg/refactor-alibi-2' into HEAD
865af990cc ggml : ggml_flash_attn_ext() support ALiBi (CUDA)
f7055d31c5 ggml : fix warning
97c27f59f6 ggml : ggml_flash_attn_ext() support ALiBi (Metal)
Compare 20 commits »
happyz synced commits to refs/pull/6784/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:43 -07:00
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)
d11afd6652 llava : fix moondream support (#7163)
Compare 7 commits »