HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced commits to refs/pull/20479/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:47 -07:00
8c16a82425 Merge 9f8d6fef78 into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 49 commits »
happyz synced commits to refs/pull/20472/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:47 -07:00
b18984c679 Merge 97ae46e460 into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 16 commits »
happyz synced commits to refs/pull/20456/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:47 -07:00
9fe7e9cc1f Merge cf7b7d2f78 into fbd441c379
fbd441c379 hexagon : add cumsum op support (#21246)
c30e012253 contrib : rewrite AGENTS.md, make it more clear about project values (#21270)
95a6ebabb2 opencl: fix leak in Adreno q8_0 path (#21212)
12dbf1da95 server: Bypass API Key validation for WebUI static bundle assets (#21269)
Compare 14 commits »
happyz synced commits to refs/pull/20453/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:47 -07:00
d2bd97a38a Merge 189ea69f76 into 744c0c7310
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
296bc0538b ggml : bump version to 0.9.10 (ggml/1454)
Compare 19 commits »
happyz synced commits to refs/pull/20451/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:47 -07:00
28255d8316 Merge 5ec6569eb5 into 8710e5f9b9
8710e5f9b9 hexagon: improve RMS_NORM and DIV accuracy (#21251)
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
Compare 16 commits »
happyz synced commits to refs/pull/20373/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:47 -07:00
029a6abe30 Merge 2266f48d68 into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 16 commits »
happyz synced commits to refs/pull/20269/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:46 -07:00
6331fddba5 Merge cfd5d05816 into 6de97b9d3e
6de97b9d3e kleidiai: add CPU feature detection to CI run script (#20394)
5a0ed5150a Update Dawn version in WebGPU CI (#20784)
8710e5f9b9 hexagon: improve RMS_NORM and DIV accuracy (#21251)
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
Compare 18 commits »
happyz synced commits to refs/pull/20172/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:46 -07:00
2bf4e432ad Merge b2a6e3f50b into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 18 commits »
happyz synced commits to refs/pull/20161/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:46 -07:00
3daf7eb052 Merge caca24bed2 into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 47 commits »
happyz synced commits to refs/pull/20125/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:45 -07:00
6fe1ac0258 Merge 630a7d456f into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 16 commits »
happyz synced commits to refs/pull/20112/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:45 -07:00
dd313fcfb1 Merge 2cf3eaf094 into 86221cf6da
86221cf6da CUDA: fix FA kernel selection logic (#21271)
6de97b9d3e kleidiai: add CPU feature detection to CI run script (#20394)
5a0ed5150a Update Dawn version in WebGPU CI (#20784)
8710e5f9b9 hexagon: improve RMS_NORM and DIV accuracy (#21251)
Compare 17 commits »
happyz synced commits to refs/pull/20086/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:45 -07:00
122a4dadcc Merge c3fb035933 into c30e012253
c30e012253 contrib : rewrite AGENTS.md, make it more clear about project values (#21270)
95a6ebabb2 opencl: fix leak in Adreno q8_0 path (#21212)
12dbf1da95 server: Bypass API Key validation for WebUI static bundle assets (#21269)
86221cf6da CUDA: fix FA kernel selection logic (#21271)
Compare 17 commits »
happyz synced commits to refs/pull/20076/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:45 -07:00
ef0aca218b Merge 9e1591780d into fbd441c379
fbd441c379 hexagon : add cumsum op support (#21246)
c30e012253 contrib : rewrite AGENTS.md, make it more clear about project values (#21270)
95a6ebabb2 opencl: fix leak in Adreno q8_0 path (#21212)
12dbf1da95 server: Bypass API Key validation for WebUI static bundle assets (#21269)
Compare 40 commits »
happyz synced commits to refs/pull/20062/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:44 -07:00
c0f6eea67e Merge 6403785b94 into fbd441c379
fbd441c379 hexagon : add cumsum op support (#21246)
c30e012253 contrib : rewrite AGENTS.md, make it more clear about project values (#21270)
95a6ebabb2 opencl: fix leak in Adreno q8_0 path (#21212)
12dbf1da95 server: Bypass API Key validation for WebUI static bundle assets (#21269)
Compare 14 commits »
happyz synced commits to refs/pull/20050/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:44 -07:00
d353fc897e Merge de30196b51 into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 17 commits »
happyz synced commits to refs/pull/20009/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:44 -07:00
b4a8f53e56 Merge b47e0cf21a into 1d6d4cf7a5
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
Compare 15 commits »
happyz synced commits to refs/pull/19987/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:44 -07:00
aea48e803a Merge 713ca906b5 into 744c0c7310
744c0c7310 llama : rotate activations for better quantization (#21038)
0356e33aaf scripts: add function call test script (#21234)
6422036fcb sync : ggml
296bc0538b ggml : bump version to 0.9.10 (ggml/1454)
Compare 31 commits »
happyz synced commits to refs/pull/19812/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:43 -07:00
672e49615b Merge 3d578b42b9 into 95a6ebabb2
95a6ebabb2 opencl: fix leak in Adreno q8_0 path (#21212)
12dbf1da95 server: Bypass API Key validation for WebUI static bundle assets (#21269)
86221cf6da CUDA: fix FA kernel selection logic (#21271)
6de97b9d3e kleidiai: add CPU feature detection to CI run script (#20394)
Compare 38 commits »
happyz synced commits to refs/pull/19670/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:43 -07:00
6a4ea993cd Merge 2124862e9b into 95a6ebabb2
95a6ebabb2 opencl: fix leak in Adreno q8_0 path (#21212)
12dbf1da95 server: Bypass API Key validation for WebUI static bundle assets (#21269)
86221cf6da CUDA: fix FA kernel selection logic (#21271)
6de97b9d3e kleidiai: add CPU feature detection to CI run script (#20394)
Compare 21 commits »
happyz synced commits to refs/pull/19590/merge at happyz/llama.cpp from mirror 2026-04-01 19:01:43 -07:00
0240ec9340 Merge 0e3a8a0c48 into 6de97b9d3e
6de97b9d3e kleidiai: add CPU feature detection to CI run script (#20394)
5a0ed5150a Update Dawn version in WebGPU CI (#20784)
8710e5f9b9 hexagon: improve RMS_NORM and DIV accuracy (#21251)
1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
Compare 35 commits »