| | __snapshots__ | |
| | test_bloom_560m_sharded.py | 1.2 KB |
| | test_bloom_560m.py | 1.7 KB |
| | test_chat_llama.py | 1.5 KB |
| | test_chat_stream_options.py | 315 B |
| | test_completion_prompts.py | 7.7 KB |
| | test_compressed_tensors_w8a8_int_dynamic_weight.py | 3.1 KB |
| | test_compressed_tensors_w8a8_int.py | 2.4 KB |
| | test_compressed_tensors_w8an_fp.py | 2.3 KB |
| | test_compressed_tensors_wna16_int_24.py | 2.4 KB |
| | test_compressed_tensors_wna16_int.py | 2.3 KB |
| | test_continue_final_message.py | 2.4 KB |
| | test_flash_awq_sharded.py | 1.5 KB |
| | test_flash_awq.py | 1.9 KB |
| | test_flash_deepseek_v2.py | 1.6 KB |
| | test_flash_falcon.py | 2.4 KB |
| | test_flash_gemma_gptq.py | 1.8 KB |
| | test_flash_gemma.py | 1.6 KB |
| | test_flash_gemma2.py | 1.6 KB |
| | test_flash_gemma3.py | 6.3 KB |
| | test_flash_gpt2.py | 1.1 KB |
| | test_flash_grammar_llama.py | 4.7 KB |
| | test_flash_llama_exl2.py | 2.0 KB |
| | test_flash_llama_fp8_kv_cache.py | 2.2 KB |
| | test_flash_llama_fp8.py | 1.9 KB |
| | test_flash_llama_gptq.py | 1.7 KB |
| | test_flash_llama_marlin_24.py | 1.8 KB |
| | test_flash_llama_marlin.py | 1.8 KB |
| | test_flash_llama_prefix_flashdecoding.py | 126.0 KB |
| | test_flash_llama_prefix.py | 125.9 KB |
| | test_flash_llama.py | 1.6 KB |
| | test_flash_medusa.py | 1.8 KB |
| | test_flash_mistral.py | 1.7 KB |
| | test_flash_mixtral_awq.py | 2.1 KB |
| | test_flash_mixtral_gptq.py | 2.1 KB |
| | test_flash_mixtral.py | 2.2 KB |
| | test_flash_neox_sharded.py | 1.3 KB |
| | test_flash_neox.py | 1.2 KB |
| | test_flash_pali_gemma.py | 1.4 KB |
| | test_flash_pali_gemma2.py | 818 B |
| | test_flash_phi.py | 1.8 KB |
| | test_flash_phi35_moe.py | 2.1 KB |
| | test_flash_qwen2_5_vl.py | 4.6 KB |
| | test_flash_qwen2_vl.py | 4.3 KB |
| | test_flash_qwen2.py | 1.8 KB |
| | test_flash_santacoder.py | 1.1 KB |
| | test_flash_starcoder_gptq.py | 1.9 KB |
| | test_flash_starcoder.py | 1.5 KB |
| | test_flash_starcoder2_lora.py | 2.1 KB |
| | test_flash_starcoder2.py | 1.5 KB |
| | test_grammar_llama.py | 2.4 KB |
| | test_grammar_response_format_llama.py | 4.0 KB |
| | test_idefics.py | 1.9 KB |
| | test_idefics2.py | 2.7 KB |
| | test_idefics3.py | 1.1 KB |
| | test_json_schema_constrain.py | 6.5 KB |
| | test_llava_next.py | 2.2 KB |
| | test_lora_mistral.py | 4.2 KB |
| | test_mamba.py | 2.0 KB |
| | test_mllama.py | 2.8 KB |
| | test_mpt.py | 1.4 KB |
| | test_mt0_base.py | 1.6 KB |
| | test_neox_sharded.py | 1.3 KB |
| | test_neox.py | 1.2 KB |
| | test_opt.py | 407 B |
| | test_smolvlm.py | 1.0 KB |
| | test_t5_sharded.py | 1.1 KB |
| | test_tools_llama.py | 17.7 KB |
| | test_transformers_llama4.py | 5.9 KB |
| | test_transformers_olmo.py | 1.1 KB |