root
0 Followers · 0 Following
  • Joined on 2024-09-10
Repositories
6
 Projects Packages Public Activity Starred Repositories
root synced commits to refs/pull/8924/merge at root/llama.cpp from mirror 2024-09-24 14:06:20 +00:00
1ab5b98852 Merge 924c832461 into 31ac5834fe
31ac5834fe llama : keep track of all EOG tokens in the vocab (#9609)
cea1486ecf log : add CONT level for continuing previous log entry (#9610)
0aa15011e3 server : add newline after chat example (#9616)
b0f27361f3 sampling : avoid expensive softmax during greedy sampling (#9605)
Compare 41 commits »
root synced commits to refs/pull/8998/merge at root/llama.cpp from mirror 2024-09-24 14:06:20 +00:00
e90212e22e Merge c90a43a2370134c634edc54457fcf1b352689db7 into 70392f1f81
70392f1f81 ggml : add AVX512DQ requirement for AVX512 builds (#9622)
bb5f819975 sync : ggml
c038931615 examples : adapt to ggml.h changes (ggml/0)
31ac5834fe llama : keep track of all EOG tokens in the vocab (#9609)
Compare 10 commits »
root synced commits to refs/pull/9090/merge at root/llama.cpp from mirror 2024-09-24 14:06:20 +00:00
183d987dc0 Merge 9373e2ba58 into 70392f1f81
70392f1f81 ggml : add AVX512DQ requirement for AVX512 builds (#9622)
bb5f819975 sync : ggml
c038931615 examples : adapt to ggml.h changes (ggml/0)
31ac5834fe llama : keep track of all EOG tokens in the vocab (#9609)
Compare 8 commits »
root synced commits to refs/pull/9449/head at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
21ee3806e4 avoid symbol link error
root synced commits to refs/pull/9449/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
d2b561d5e3 Merge 21ee3806e4 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
21ee3806e4 avoid symbol link error
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 4 commits »
root synced commits to refs/pull/9482/head at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
46d20e11e2 Updated clip.cpp
36d9bbce6b Updated examples/llava/clip.cpp
Compare 2 commits »
root synced commits to refs/pull/9482/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
0920a42d29 Merge 46d20e11e2 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
46d20e11e2 Updated clip.cpp
36d9bbce6b Updated examples/llava/clip.cpp
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 5 commits »
root synced commits to refs/pull/9510/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
7f0927550e Merge 5b6468fba509fa0d95b5090e9f05d707b2c26de8 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »
root synced commits to refs/pull/9525/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
0cf0d09acb Merge 95ce058c2bc361f600229e3a7954ff45c479bf95 into 116efee0ee
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 2 commits »
root synced commits to refs/pull/9541/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
8760110f05 Merge c42ec2f8bb into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
0b3bf966f4 server : add --no-context-shift option (#9607)
f0c7b5edf8 threads: improve ggml_barrier scaling with large number of threads (#9598)
Compare 5 commits »
root synced commits to refs/pull/9557/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
1bc1ae4d96 Merge f9c2155158 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
0b3bf966f4 server : add --no-context-shift option (#9607)
f0c7b5edf8 threads: improve ggml_barrier scaling with large number of threads (#9598)
Compare 8 commits »
root synced commits to refs/pull/9591/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
45138503ca Merge c7081061a9 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »
root synced commits to refs/pull/9592/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
a333232781 Merge 5066f51f671ab04f5988b4becafdf62188581759 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »
root synced commits to refs/pull/9594/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
83eca9040a Merge 0c277a290a68c11a089cb457097a88e25b4a9fe1 into 0b3bf966f4
0b3bf966f4 server : add --no-context-shift option (#9607)
f0c7b5edf8 threads: improve ggml_barrier scaling with large number of threads (#9598)
Compare 3 commits »
root synced commits to refs/pull/9597/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
75eb737de6 Merge 86fd30d122b6e811d3a0f90b004a282f390c8168 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
0b3bf966f4 server : add --no-context-shift option (#9607)
f0c7b5edf8 threads: improve ggml_barrier scaling with large number of threads (#9598)
Compare 5 commits »
root synced commits to refs/pull/9602/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
f7254436f4 Merge bfb1058d74 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »
root synced commits to refs/pull/9603/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
71117407be Merge 3578d09729 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »
root synced commits to refs/pull/9604/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
b7190dcba9 Merge 114ab6347e into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »
root synced commits to refs/pull/9605/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
6dc29ba167 Merge a5a11bfbc3 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »
root synced commits to refs/pull/9609/merge at root/llama.cpp from mirror 2024-09-24 05:56:22 +00:00
c6d6347fb4 Merge a2393d6f08 into c087b6f11d
c087b6f11d threads: fix msvc build without openmp (#9615)
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
Compare 3 commits »