HappyZ

happyz synced commits to refs/pull/6965/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:47 -07:00

b0b22bdf9f Merge ea47119736 into 4426e2987b

4426e2987b cmake : fix typo (#7151)

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

ea47119736 Merge branch 'master' into gg/bpe-preprocess

77cbb79532 Refactor random tokenizer test

Compare 42 commits »

happyz synced commits to refs/pull/6940/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:47 -07:00

19e287d4e0 Merge 7666c4c059 into 4426e2987b

4426e2987b cmake : fix typo (#7151)

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

Compare 19 commits »

happyz synced commits to refs/pull/6999/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:47 -07:00

5542cec719 Merge 9a8db6b2b4b54d1da178fd7c961839276fd98e52 into 83330d8cd6

83330d8cd6 main : add --conversation / -cnv flag (#7108)

465263d0cf sgemm : AVX Q4_0 and Q8_0 (#6891)

Compare 3 commits »

happyz synced commits to refs/pull/6958/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:47 -07:00

85b58a7306 Merge 93af09a030 into 83330d8cd6

83330d8cd6 main : add --conversation / -cnv flag (#7108)

465263d0cf sgemm : AVX Q4_0 and Q8_0 (#6891)

Compare 3 commits »

happyz synced commits to refs/pull/6951/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:47 -07:00

f45be45a52 Merge 2ff76f2458 into bc4bba364f

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

9da243b36a Revert "llava : add support for moondream vision language model (#6899)"

bd1871fa2b server : add themes + favicon (#6848)

Compare 8 commits »

happyz synced commits to refs/pull/6965/head at happyz/llama.cpp from mirror 2024-05-08 18:38:47 -07:00

ea47119736 Merge branch 'master' into gg/bpe-preprocess

77cbb79532 Refactor random tokenizer test

70ca1fe204 Clean gen-unicode-data.py

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

Compare 39 commits »

happyz synced commits to refs/pull/6869/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:46 -07:00

782d87703e Merge cf9dca34cbd02c89fb3f3c46e85da817fe89744b into f98eb31c51

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

9da243b36a Revert "llava : add support for moondream vision language model (#6899)"

Compare 14 commits »

happyz synced commits to refs/pull/6919/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:46 -07:00

94106ff8ea Merge a76fbcd050 into 4426e2987b

4426e2987b cmake : fix typo (#7151)

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

Compare 10 commits »

happyz synced commits to refs/pull/6915/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:46 -07:00

f3fac588d7 Merge e2dcf468dc40866ff4468bdc0b41d61bbaf5caec into 4426e2987b

4426e2987b cmake : fix typo (#7151)

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

Compare 10 commits »

happyz synced commits to refs/pull/6888/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:46 -07:00

1200827b08 Merge 2ef86e7213 into 83330d8cd6

83330d8cd6 main : add --conversation / -cnv flag (#7108)

465263d0cf sgemm : AVX Q4_0 and Q8_0 (#6891)

911b3900dd server : add_special option for tokenize endpoint (#7059)

ad211edef5 convert.py : --vocab-only generates false but valid params (#7027)

Compare 29 commits »

happyz synced commits to refs/pull/6839/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:45 -07:00

f31a92f5fd Merge 49e078f79d into 4426e2987b

4426e2987b cmake : fix typo (#7151)

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

Compare 10 commits »

happyz synced commits to refs/pull/6834/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:45 -07:00

4de5fae2f1 Merge 8fe8231313 into 911b3900dd

8fe8231313 ChatON:SubPartsAwareTokenizePath: Allow extract subparts testing

a49697b488 ChatON: Keep compiler happy simbly

0d81ffe6eb Tests:ChatON: Add partial skeleton wrt subparts tokenizing

Compare 4 commits »

happyz synced commits to refs/pull/6834/head at happyz/llama.cpp from mirror 2024-05-08 18:38:45 -07:00

8fe8231313 ChatON:SubPartsAwareTokenizePath: Allow extract subparts testing

a49697b488 ChatON: Keep compiler happy simbly

0d81ffe6eb Tests:ChatON: Add partial skeleton wrt subparts tokenizing

Compare 3 commits »

happyz synced commits to refs/pull/6829/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:45 -07:00

b0aea23612 Merge de1cf88601a527d6869696ff3f2c1cefb30b2f42 into 4426e2987b

4426e2987b cmake : fix typo (#7151)

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

Compare 10 commits »

happyz synced commits to refs/pull/6811/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:44 -07:00

217ec18b8d Merge 80736c556b into c12452c7ae

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

9da243b36a Revert "llava : add support for moondream vision language model (#6899)"

bd1871fa2b server : add themes + favicon (#6848)

26458af1d6 metal : use `vm_allocate` instead of `posix_memalign` on macOS (#7078)

Compare 18 commits »

happyz synced commits to refs/pull/6826/head at happyz/llama.cpp from mirror 2024-05-08 18:38:44 -07:00

8e36fd5a70 Merge branch 'master' of https://github.com/JoanFM/llama.cpp into feat-jina-embeddings

b7ede48294 llama : fix pre-tokenizers

83330d8cd6 main : add --conversation / -cnv flag (#7108)

465263d0cf sgemm : AVX Q4_0 and Q8_0 (#6891)

e59b54657a Merge branch 'master' into feat-jina-embeddings

Compare 26 commits »

happyz synced commits to refs/pull/6826/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:44 -07:00

11e5b74e47 Merge 8e36fd5a70 into bc4bba364f

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

9da243b36a Revert "llava : add support for moondream vision language model (#6899)"

bd1871fa2b server : add themes + favicon (#6848)

Compare 12 commits »

happyz synced commits to refs/pull/6766/head at happyz/llama.cpp from mirror 2024-05-08 18:38:44 -07:00

f42312e0a1 replace minimum cc value with a constant

ab40e667dd remove outdated comment

Compare 2 commits »

happyz synced commits to refs/pull/6778/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:44 -07:00

4a31c76791 Merge 158215c828 into bc4bba364f

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

9da243b36a Revert "llava : add support for moondream vision language model (#6899)"

bd1871fa2b server : add themes + favicon (#6848)

Compare 8 commits »

happyz synced commits to refs/pull/6522/merge at happyz/llama.cpp from mirror 2024-05-08 18:38:43 -07:00

f6e4240bbf Merge a37d88568336ec949865e166eaf1454841f4cdb5 into 4426e2987b

4426e2987b cmake : fix typo (#7151)

f98eb31c51 convert-hf : save memory with lazy evaluation (#7075)

bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766)

c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)

Compare 45 commits »