text-generation-inference/integration-tests/models/__snapshots__
Daniël de Kok 84ab88d843
Support flashinfer for Gemma3 prefill (#3167)
* launcher: ensure correct detection of Gemma 3 head size

* Support flashinfer for Gemma3 prefill

Gemma3 uses bidirectional attention for images. Flashinfer
supports custom masks. Hook up the mask with flashinfer, so that we do
not have to use the slower SDPA implementation for prefills with images.

* Update Gemma3 test outputs

* Fixed unused import
2025-04-17 18:07:41 +02:00
..
test_bloom_560m
test_bloom_560m_sharded
test_chat_llama
test_completion_prompts
test_compressed_tensors_w8a8_int
test_compressed_tensors_w8a8_int_dynamic_weight
test_compressed_tensors_w8an_fp
test_compressed_tensors_wna16_int
test_compressed_tensors_wna16_int_24
test_continue_final_message
test_flash_awq
test_flash_awq_sharded
test_flash_deepseek_v2
test_flash_falcon
test_flash_gemma
test_flash_gemma2
test_flash_gemma3
test_flash_gemma_gptq
test_flash_gpt2
test_flash_grammar_llama
test_flash_llama
test_flash_llama_exl2
test_flash_llama_fp8
test_flash_llama_fp8_kv_cache
test_flash_llama_gptq
test_flash_llama_marlin
test_flash_llama_marlin_24
test_flash_llama_prefix
test_flash_llama_prefix_flashdecoding
test_flash_medusa
test_flash_mistral
test_flash_mixtral
test_flash_mixtral_awq
test_flash_mixtral_gptq
test_flash_neox
test_flash_neox_sharded
test_flash_pali_gemma
test_flash_pali_gemma2
test_flash_phi
test_flash_phi35_moe
test_flash_qwen2
test_flash_qwen2_5_vl
test_flash_qwen2_vl
test_flash_santacoder
test_flash_starcoder
test_flash_starcoder2
test_flash_starcoder2_lora
test_flash_starcoder_gptq
test_grammar_llama
test_grammar_response_format_llama
test_idefics
test_idefics2
test_idefics3
test_llava_next
test_lora_mistral
test_mamba
test_mllama
test_mpt
test_mt0_base
test_neox
test_neox_sharded
test_server_gptq_quantized
test_smolvlm
test_t5_sharded
test_tools_llama
test_transformers_llama4
test_transformers_olmo
test.py