284 kB

Ctrl+K

1 contributor

History: 1 commit

kat0012

Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7)

d2816aa verified 20 days ago

test_basic.py

3.4 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_chat_completion.py

24.9 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_compat_anthropic.py

36.7 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_compat_gcp.py

1.8 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_compat_oai_responses.py

3.83 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_completion.py

24.3 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_ctx_shift.py

3.1 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_embedding.py

8.97 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_ignore_eos.py

1.27 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_infill.py

2.58 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_kv_keep_only_active.py

3.52 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_lora.py

4.63 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_mcp_servers.py

24.4 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_metrics.py

7.78 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_proxy.py

1.88 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_rerank.py

4.84 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_router.py

20.2 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_security.py

8.43 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_sleep.py

3.84 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_slot_save.py

18.7 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_speculative.py

6.09 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_stream.py

5.44 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_template.py

3.99 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_tokenize.py

1.57 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_tool_call.py

35.7 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_tools_builtin.py

15.5 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago
test_vision_api.py

7.06 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7) 20 days ago