HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced commits to refs/pull/6403/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:09 -07:00
ab62084cd9 Merge 095647bf5d into 784e11dea1
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
3fe847b574 server : do not apply Markdown formatting in code sections (#6850)
37246b1031 common : revert showing control tokens by default for server (#6860)
Compare 8 commits »
happyz synced commits to refs/pull/6408/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:09 -07:00
58ce964e94 Merge de8851868dd27651c941b8534ff32f2a612b4905 into fa0b4ad252
fa0b4ad252 cmake : remove obsolete ANDROID check
d6e1d44f16 llama : synchronize before get/set session data (#6911)
853d06ffe2 ci : tmp disable slow tests
3fe0596c18 readme : update model list (#6908)
Compare 152 commits »
happyz synced commits to refs/pull/6389/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:09 -07:00
a3c6d9bf3c Merge 9126de013a4d8cabde26b4d03267b49f5819c3ce into 784e11dea1
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
3fe847b574 server : do not apply Markdown formatting in code sections (#6850)
37246b1031 common : revert showing control tokens by default for server (#6860)
Compare 5 commits »
happyz synced commits to refs/pull/6371/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:09 -07:00
fdcb7df435 Merge 63eaed650b into aa750c1ede
aa750c1ede tests : minor bash stuff (#6902)
1966eb2615 quantize : add '--keep-split' to quantize model into shards (#6688)
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
Compare 12 commits »
happyz synced commits to refs/pull/6312/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:08 -07:00
ddb824afc8 Merge 1440d445db into 54770413c4
54770413c4 ggml : fix MIN / MAX macros (#6904)
aa750c1ede tests : minor bash stuff (#6902)
1966eb2615 quantize : add '--keep-split' to quantize model into shards (#6688)
784e11dea1 README: add graphic for matrix multiplication (#6881)
Compare 13 commits »
happyz synced commits to refs/pull/6035/head at happyz/llama.cpp from mirror 2024-04-25 11:14:08 -07:00
a20298a6d5 add softmax_ext
f1bde5d5d3 add ascend kernel compile struct
352839934c add alibi & fix double release in timestep_embedding
9cd7fb489c release tensorlist outside aclnn_concat
ddf8517f04 Change cmake to support compile ascendc kernels
Compare 121 commits »
happyz synced commits to refs/pull/6035/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:08 -07:00
fc742112c5 Merge a20298a6d5a55d22e12868111df3b1b13612c6dd into 853d06ffe2
853d06ffe2 ci : tmp disable slow tests
3fe0596c18 readme : update model list (#6908)
0ead1f1072 llama : check that all the tensor data is in the model file (#6885)
a20298a6d5 add softmax_ext
Compare 70 commits »
happyz synced commits to refs/pull/6358/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:08 -07:00
bfe1f73af8 Merge 275ccea394 into 784e11dea1
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
3fe847b574 server : do not apply Markdown formatting in code sections (#6850)
37246b1031 common : revert showing control tokens by default for server (#6860)
Compare 10 commits »
happyz synced commits to refs/pull/5677/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:07 -07:00
73dc9a797c Merge 593627a8b1 into 784e11dea1
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
3fe847b574 server : do not apply Markdown formatting in code sections (#6850)
37246b1031 common : revert showing control tokens by default for server (#6860)
Compare 16 commits »
happyz synced commits to refs/pull/5730/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:07 -07:00
327aac6219 Merge 8ac7656bd1 into aa750c1ede
aa750c1ede tests : minor bash stuff (#6902)
1966eb2615 quantize : add '--keep-split' to quantize model into shards (#6688)
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
Compare 12 commits »
happyz synced commits to refs/pull/5615/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:07 -07:00
9b4efdee69 Merge 941de11759 into 784e11dea1
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
3fe847b574 server : do not apply Markdown formatting in code sections (#6850)
37246b1031 common : revert showing control tokens by default for server (#6860)
Compare 12 commits »
happyz synced commits to refs/pull/5385/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:07 -07:00
4abe5634f0 Merge 914922d27e into 784e11dea1
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
3fe847b574 server : do not apply Markdown formatting in code sections (#6850)
37246b1031 common : revert showing control tokens by default for server (#6860)
Compare 10 commits »
happyz synced commits to refs/pull/5021/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:07 -07:00
b9511cc13c Merge 9e3876061c into fa0b4ad252
9e3876061c llama : add static reminder for llama_state_get_size
4f4c0249bf metal : remove tmp log
1e590ac3c9 llama : update llama_state_get_size after v_trans field
0fc5c5eb74 llama : disallow incompatible states
Compare 24 commits »
happyz synced commits to sl/check-tensor at happyz/llama.cpp from mirror 2024-04-25 11:14:06 -07:00
happyz synced commits to master at happyz/llama.cpp from mirror 2024-04-25 11:14:06 -07:00
fa0b4ad252 cmake : remove obsolete ANDROID check
d6e1d44f16 llama : synchronize before get/set session data (#6911)
853d06ffe2 ci : tmp disable slow tests
3fe0596c18 readme : update model list (#6908)
0ead1f1072 llama : check that all the tensor data is in the model file (#6885)
Compare 11 commits »
happyz synced new reference sl/check-tensor to happyz/llama.cpp from mirror 2024-04-25 11:14:06 -07:00
happyz synced commits to sycl-refactor at happyz/llama.cpp from mirror 2024-04-25 11:14:06 -07:00
de8851868d seperate dpct helper functions
51543729ff ggml : fix redefinition of vaddvq_f32 for 32-bit ARM (#6906)
4ab99d8d47 clip : rename lerp function to avoid conflict (#6894)
54770413c4 ggml : fix MIN / MAX macros (#6904)
aa750c1ede tests : minor bash stuff (#6902)
Compare 150 commits »
happyz synced commits to refs/pull/1132/merge at happyz/llama.cpp from mirror 2024-04-25 11:14:06 -07:00
a60ab51100 Merge b1a8c244ce into 784e11dea1
784e11dea1 README: add graphic for matrix multiplication (#6881)
b4e4b8a935 llama : add llama_get_pooling_type function (#6862)
3fe847b574 server : do not apply Markdown formatting in code sections (#6850)
37246b1031 common : revert showing control tokens by default for server (#6860)
Compare 141 commits »
happyz synced commits to refs/pull/5021/head at happyz/llama.cpp from mirror 2024-04-25 11:14:06 -07:00
9e3876061c llama : add static reminder for llama_state_get_size
4f4c0249bf metal : remove tmp log
1e590ac3c9 llama : update llama_state_get_size after v_trans field
0fc5c5eb74 llama : disallow incompatible states
bab346ba69 llama : fix copy-paste errors, add TODO
Compare 24 commits »
happyz synced new reference gg/fix-min-max to happyz/llama.cpp from mirror 2024-04-25 11:14:05 -07:00