drbh 0b95693fb8 fix: adjust test snapshots and small refactors (#2323) ... * fix: adjust test snapshots and small refactors * fix: revert non snapshot changes		2024-07-29 11:38:38 -04:00
..
test_bloom_560m	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_bloom_560m_sharded	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_chat_llama	…
test_completion_prompts	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_flash_awq	…
test_flash_awq_sharded	…
test_flash_deepseek_v2	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_flash_falcon	…
test_flash_gemma	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_flash_gemma2	Softcapping for gemma2. (#2273)	2024-07-22 18:27:10 +02:00
test_flash_gemma_gptq	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_flash_gpt2	…
test_flash_grammar_llama	…
test_flash_llama	…
test_flash_llama_exl2	…
test_flash_llama_fp8	fix(server): fix fp8 weight loading (#2268)	2024-07-22 15:51:32 +00:00
test_flash_llama_gptq	…
test_flash_llama_marlin	…
test_flash_llama_marlin_24	…
test_flash_medusa	…
test_flash_mistral	…
test_flash_neox	…
test_flash_neox_sharded	…
test_flash_pali_gemma	Some small fixes for the Torch 2.4.0 update (#2304)	2024-07-25 13:34:44 +02:00
test_flash_phi	…
test_flash_qwen2	…
test_flash_santacoder	…
test_flash_starcoder	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_flash_starcoder2	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_flash_starcoder_gptq	…
test_grammar_llama	…
test_grammar_response_format_llama	…
test_idefics	…
test_idefics2	Fixing idefics on g6 tests. (#2306)	2024-07-25 14:44:21 +02:00
test_llava_next	…
test_lora_mistral	…
test_mamba	fix: adjust test snapshots and small refactors (#2323)	2024-07-29 11:38:38 -04:00
test_mpt	…
test_mt0_base	…
test_neox	…
test_neox_sharded	…
test_server_gptq_quantized	…
test_t5_sharded	…
test_tools_llama	…