HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced commits to refs/pull/2950/merge at happyz/memos from mirror 2024-04-17 11:12:51 -07:00
1012e3e78d Merge d9e1d8d231 into 2cdcd17ba3
2cdcd17ba3 chore: tweak linter
14d4cfd5a4 chore: tweak store methods name
00d25b12c1 chore: translated using Weblate (Russian) (#3245)
95df647265 chore: tweak comments
Compare 14 commits »
happyz synced new reference refs/tags/b2687 to happyz/llama.cpp from mirror 2024-04-16 23:13:15 -07:00
happyz synced new reference refs/tags/b2686 to happyz/llama.cpp from mirror 2024-04-16 23:13:14 -07:00
happyz synced commits to refs/tags/b2686 at happyz/llama.cpp from mirror 2024-04-16 23:13:14 -07:00
happyz synced commits to refs/pull/6707/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:14 -07:00
2fa66620dd Merge 8dd93aa06d into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 5 commits »
happyz synced commits to refs/tags/b2687 at happyz/llama.cpp from mirror 2024-04-16 23:13:14 -07:00
happyz synced commits to refs/pull/6697/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:13 -07:00
440a324461 Merge ec3cc36dc8 into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 5 commits »
happyz synced commits to refs/pull/6661/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:13 -07:00
2a3cfc2d34 Merge b9286a4d7b into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 7 commits »
happyz synced commits to refs/pull/6658/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:13 -07:00
ef74a96343 Merge 0d82da6f79 into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 5 commits »
happyz synced commits to refs/pull/6688/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:13 -07:00
834426ccfa Merge 17519e110f into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 7 commits »
happyz synced commits to refs/pull/6646/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:12 -07:00
aed43c2c80 Merge 1ca64545a8a956414f00fde564792c9f90a75b0a into 89961dea87
1ca64545a8 Calculate KQ as FP32 if KQV has GGML_PREC_F32
3277629bf4 store temp KQ in registers
Compare 3 commits »
happyz synced commits to refs/pull/6644/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:12 -07:00
1f4a557c30 Merge 1b988855dca2ced3850dbe40812707e639b1dbd6 into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 7 commits »
happyz synced commits to refs/pull/6640/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:12 -07:00
7c2c5d7908 Merge 1fb778750f into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 5 commits »
happyz synced commits to refs/pull/6648/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:12 -07:00
8a4df2cf57 Merge ab2fae200c into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 5 commits »
happyz synced commits to refs/pull/6646/head at happyz/llama.cpp from mirror 2024-04-16 23:13:12 -07:00
1ca64545a8 Calculate KQ as FP32 if KQV has GGML_PREC_F32
3277629bf4 store temp KQ in registers
Compare 2 commits »
happyz synced commits to refs/pull/6602/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:11 -07:00
ea44d4b06c Merge 1cd0a03720 into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 5 commits »
happyz synced commits to refs/pull/6578/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:11 -07:00
b894d97809 Merge daa4f259c3 into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 7 commits »
happyz synced commits to refs/pull/6522/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:11 -07:00
cba167fec4 Merge a37d88568336ec949865e166eaf1454841f4cdb5 into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 5 commits »
happyz synced commits to refs/pull/6638/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:11 -07:00
f85d729fc0 Merge 6fd5ad597f into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 7 commits »
happyz synced commits to refs/pull/6502/merge at happyz/llama.cpp from mirror 2024-04-16 23:13:10 -07:00
0c9324d8f1 Merge 48fbf8ca1a into facb8b56f8
facb8b56f8 convert : fix autoawq gemma (#6704)
532c1737a1 llama : make general.name optional (#6709)
666867b799 ggml : fix llamafile sgemm wdata offsets (#6710)
8cc91dc63c ggml : add llamafile sgemm (#6414)
Compare 10 commits »