HappyZ happyz
happyz synced commits to refs/pull/6312/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:48 -07:00
e00b4a8f81 Fix more int overflow during quant (PPL/CUDA). (#6563)
7bb36ccf91 gguf : enforce that tensor names are unique (#6905)
ce023f6f2f add device version in device list (#6959)
6e472f58e4 flake.lock: Update
Compare 5 commits »
happyz synced commits to refs/pull/6307/head at happyz/llama.cpp from mirror 2024-04-29 10:18:48 -07:00
9d6f198bfe Update llava-cli.cpp
5e906de275 Update llava-cli.cpp
e441cc8992 Update examples/llava/llava-cli.cpp
Compare 3 commits »
happyz synced commits to refs/pull/6035/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:48 -07:00
b7ad9c5978 Merge 94610511daf7d2ccac8c5ff047da43e5a99cad77 into b8a7a5a90f
b8a7a5a90f build(cmake): simplify instructions (`cmake -B build && cmake --build build ...`) (#6964)
d2c898f746 ci : tmp disable gguf-split (#6983)
544f1f10ad ggml : fix __MSC_VER -> _MSC_VER (#6977)
ffe666572f llava-cli : multiple images (#6969)
Compare 16 commits »
happyz synced commits to refs/pull/6389/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:48 -07:00
b8a7a5a90f build(cmake): simplify instructions (`cmake -B build && cmake --build build ...`) (#6964)
d2c898f746 ci : tmp disable gguf-split (#6983)
544f1f10ad ggml : fix __MSC_VER -> _MSC_VER (#6977)
ffe666572f llava-cli : multiple images (#6969)
Compare 15 commits »
happyz synced commits to refs/pull/4311/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:47 -07:00
ffa782d883 Merge 2de1cb589499a9ed4b043b65a13a6e4d3db749ef into e00b4a8f81
e00b4a8f81 Fix more int overflow during quant (PPL/CUDA). (#6563)
7bb36ccf91 gguf : enforce that tensor names are unique (#6905)
ce023f6f2f add device version in device list (#6959)
6e472f58e4 flake.lock: Update
Compare 35 commits »
happyz synced commits to refs/pull/5021/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:47 -07:00
b8a7a5a90f build(cmake): simplify instructions (`cmake -B build && cmake --build build ...`) (#6964)
ca0275ceb7 Merge branch 'master' into gg/flash-attn
d2c898f746 ci : tmp disable gguf-split (#6983)
544f1f10ad ggml : fix __MSC_VER -> _MSC_VER (#6977)
Compare 15 commits »
happyz synced commits to refs/pull/5021/head at happyz/llama.cpp from mirror 2024-04-29 10:18:47 -07:00
ca0275ceb7 Merge branch 'master' into gg/flash-attn
d2c898f746 ci : tmp disable gguf-split (#6983)
544f1f10ad ggml : fix __MSC_VER -> _MSC_VER (#6977)
ffe666572f llava-cli : multiple images (#6969)
a1616e9f72 Merge branch 'master' into gg/flash-attn
Compare 32 commits »
happyz synced commits to refs/pull/5891/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:47 -07:00
ffe666572f llava-cli : multiple images (#6969)
24affa7db3 readme : update hot topics
f4ab2a4147 llama : fix BPE pre-tokenization (#6920)
3f167476b1 sampling : use std::random_device{}() for default random seed (#6962)
Compare 13 commits »
happyz synced commits to refs/pull/5730/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:47 -07:00
544f1f10ad ggml : fix __MSC_VER -> _MSC_VER (#6977)
ffe666572f llava-cli : multiple images (#6969)
24affa7db3 readme : update hot topics
f4ab2a4147 llama : fix BPE pre-tokenization (#6920)
Compare 13 commits »
happyz synced new reference gg/tmp-ci to happyz/llama.cpp from mirror 2024-04-29 10:18:46 -07:00
happyz synced commits to gg/tmp-ci at happyz/llama.cpp from mirror 2024-04-29 10:18:46 -07:00
happyz synced commits to gg/flash-attn at happyz/llama.cpp from mirror 2024-04-29 10:18:46 -07:00
ca0275ceb7 Merge branch 'master' into gg/flash-attn
d2c898f746 ci : tmp disable gguf-split (#6983)
544f1f10ad ggml : fix __MSC_VER -> _MSC_VER (#6977)
ffe666572f llava-cli : multiple images (#6969)
a1616e9f72 Merge branch 'master' into gg/flash-attn
Compare 32 commits »
happyz synced commits to master at happyz/llama.cpp from mirror 2024-04-29 10:18:46 -07:00
b8a7a5a90f build(cmake): simplify instructions (`cmake -B build && cmake --build build ...`) (#6964)
d2c898f746 ci : tmp disable gguf-split (#6983)
544f1f10ad ggml : fix __MSC_VER -> _MSC_VER (#6977)
ffe666572f llava-cli : multiple images (#6969)
24affa7db3 readme : update hot topics
Compare 12 commits »
happyz synced commits to refs/pull/4012/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:46 -07:00
f4ab2a4147 llama : fix BPE pre-tokenization (#6920)
3f167476b1 sampling : use std::random_device{}() for default random seed (#6962)
3055a41805 convert : fix conversion of some BERT embedding models (#6937)
577277ffd2 make : change GNU make default CXX from g++ to c++ (#6966)
Compare 13 commits »
happyz synced and deleted reference refs/tags/refs/pull/6962/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:45 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6920/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:45 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6937/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:45 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6964/merge at happyz/llama.cpp from mirror 2024-04-29 10:18:45 -07:00
happyz synced commits to gg/bpe-preprocess at happyz/llama.cpp from mirror 2024-04-29 10:18:45 -07:00
80cb3127df tests : disable test-tokenizer-1-bpe due to slowness
3202676f5d llama : more prominent warning for old BPE models
6d6ce93959 tests : use faster bpe test
9a7d430ff2 tests : disable obsolete
120cf37d54 models : add phi-3, mpt, gpt-2, starcoder
Compare 19 commits »
happyz synced commits to compilade/refactor-kv-cache at happyz/llama.cpp from mirror 2024-04-29 10:18:45 -07:00
b6fafd1747 llama : remove useless return value for some llama_cache_* functions
c460ff1a1c Merge branch 'master' into compilade/refactor-kv-cache
a09db95eab llama : rename many llama_kv_cache_* functions
24affa7db3 readme : update hot topics
f4ab2a4147 llama : fix BPE pre-tokenization (#6920)
Compare 125 commits »