HappyZ happyz
happyz synced commits to refs/pull/7326/merge at happyz/llama.cpp from mirror 2024-05-21 11:06:00 -07:00
fcf6538ba6 CUDA: fix unused warning in mmq.cu (#7442)
c3f8d58356 tests : test-tokenizer-0.sh print more info (#7402)
c0cc883ae9 Added nproc for systems that don't default to nproc
11474e756d examples: cache hf model when --model not provided (#7353)
Compare 7 commits »
happyz synced commits to refs/pull/7326/head at happyz/llama.cpp from mirror 2024-05-21 11:06:00 -07:00
c0cc883ae9 Added nproc for systems that don't default to nproc
happyz synced commits to refs/pull/7239/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:59 -07:00
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
Compare 18 commits »
happyz synced commits to refs/pull/7285/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:59 -07:00
c3f8d58356 tests : test-tokenizer-0.sh print more info (#7402)
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
Compare 12 commits »
happyz synced commits to refs/pull/7270/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:59 -07:00
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
Compare 4 commits »
happyz synced commits to refs/pull/7267/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:59 -07:00
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
Compare 4 commits »
happyz synced commits to refs/pull/7229/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:59 -07:00
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
Compare 27 commits »
happyz synced commits to refs/pull/7225/head at happyz/llama.cpp from mirror 2024-05-21 11:05:58 -07:00
92711138f9 convert : read/write n_head_kv
e9acbce624 cuda : fix compile warning
23b72b871c llama : remove tmp assert
600896b882 llama : move rope factors from KV header to tensors
d93b5cad0a minor : cleanup
Compare 76 commits »
happyz synced commits to refs/pull/7225/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:58 -07:00
fcf6538ba6 CUDA: fix unused warning in mmq.cu (#7442)
c3f8d58356 tests : test-tokenizer-0.sh print more info (#7402)
92711138f9 convert : read/write n_head_kv
e9acbce624 cuda : fix compile warning
Compare 29 commits »
happyz synced commits to refs/pull/6923/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:57 -07:00
c3f8d58356 tests : test-tokenizer-0.sh print more info (#7402)
12fcea5d04 llama: rename llama_token_is_control_token() to llama_token_is_control()
d8b373c146 Merge branch 'master' into grammar-token
11474e756d examples: cache hf model when --model not provided (#7353)
Compare 17 commits »
happyz synced commits to refs/pull/6923/head at happyz/llama.cpp from mirror 2024-05-21 11:05:57 -07:00
12fcea5d04 llama: rename llama_token_is_control_token() to llama_token_is_control()
d8b373c146 Merge branch 'master' into grammar-token
8f76ba54ba main: refactor ctrl_token_no_out --> no_special
7d52482bac main: renamed --no-special from --ctrl-token-no-out and other refactoring
c1e8a6d1c0 main: must check pipe status on very top of program
Compare 47 commits »
happyz synced commits to refs/pull/6988/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:57 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
Compare 3 commits »
happyz synced commits to refs/pull/6919/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:57 -07:00
c3f8d58356 tests : test-tokenizer-0.sh print more info (#7402)
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
Compare 5 commits »
happyz synced commits to refs/pull/6389/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:56 -07:00
5ea637e42c openai: fix merge
c3f8d58356 tests : test-tokenizer-0.sh print more info (#7402)
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
Compare 6 commits »
happyz synced commits to refs/pull/6839/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:56 -07:00
fcf6538ba6 CUDA: fix unused warning in mmq.cu (#7442)
c3f8d58356 tests : test-tokenizer-0.sh print more info (#7402)
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
Compare 6 commits »
happyz synced commits to refs/pull/6640/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:56 -07:00
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
Compare 5 commits »
happyz synced commits to refs/pull/6840/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:56 -07:00
ba3126e9dc Merge bb3a5274c7c1efd883f7e57edb849c0394d2c91d into 11474e756d
11474e756d examples: cache hf model when --model not provided (#7353)
d8ee902227 CUDA: deduplicate mmq code (#7397)
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
Compare 4 commits »
happyz synced commits to refs/pull/6445/merge at happyz/llama.cpp from mirror 2024-05-21 11:05:56 -07:00
d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
Compare 2 commits »
happyz synced commits to refs/pull/6035/head at happyz/llama.cpp from mirror 2024-05-21 11:05:55 -07:00
bf69afb867 add rope fp16
happyz synced commits to refs/pull/6389/head at happyz/llama.cpp from mirror 2024-05-21 11:05:55 -07:00
5ea637e42c openai: fix merge