Merge tag 'v0.8.4' into v0.8.4-ori

9c4ecf15 · zhuwenwen · bfc2d6f7 · dc1b4a6f · 9c4ecf15 · 9c4ecf15
Commit 9c4ecf15 authored Apr 14, 2025 by zhuwenwen
20 changed files
--- a/tests/kernels/test_block_int8.py
+++ b/tests/kernels/test_block_int8.py
--- a/tests/kernels/test_flashmla.py
+++ b/tests/kernels/test_flashmla.py
--- a/tests/kernels/test_int8_kernel.py
+++ b/tests/kernels/test_int8_kernel.py
--- a/tests/kernels/test_merge_attn_states.py
+++ b/tests/kernels/test_merge_attn_states.py
--- a/tests/kernels/test_triton_moe_ptpc_fp8.py
+++ b/tests/kernels/test_triton_moe_ptpc_fp8.py
--- a/tests/kernels/utils_block.py
+++ b/tests/kernels/utils_block.py
--- a/tests/lora/conftest.py
+++ b/tests/lora/conftest.py
--- a/tests/lora/test_baichuan.py
+++ b/tests/lora/test_baichuan.py
--- a/tests/lora/test_chatglm3_tp.py
+++ b/tests/lora/test_chatglm3_tp.py
--- a/tests/lora/test_layers.py
+++ b/tests/lora/test_layers.py
--- a/tests/lora/test_llama_tp.py
+++ b/tests/lora/test_llama_tp.py
--- a/tests/lora/test_punica_ops.py
+++ b/tests/lora/test_punica_ops.py
--- a/tests/lora/test_quant_model.py
+++ b/tests/lora/test_quant_model.py
--- a/tests/lora/test_transfomers_model.py
+++ b/tests/lora/test_transfomers_model.py
--- a/tests/models/decoder_only/audio_language/test_ultravox.py
+++ b/tests/models/decoder_only/audio_language/test_ultravox.py
--- a/tests/models/decoder_only/language/test_gguf.py
+++ b/tests/models/decoder_only/language/test_gguf.py
--- a/tests/models/decoder_only/vision_language/test_models.py
+++ b/tests/models/decoder_only/vision_language/test_models.py
--- a/tests/models/decoder_only/vision_language/test_phi3v.py
+++ b/tests/models/decoder_only/vision_language/test_phi3v.py
--- a/tests/models/decoder_only/vision_language/test_phi4mm.py
+++ b/tests/models/decoder_only/vision_language/test_phi4mm.py
--- a/tests/models/decoder_only/vision_language/test_pixtral.py
+++ b/tests/models/decoder_only/vision_language/test_pixtral.py