Merge tag 'v0.5.4' into v0.5.4-dtk24.04.1

e661d594 · zhuwenwen · 6b16ea2e · 4db5176d · e661d594 · e661d594
Commit e661d594 authored Aug 12, 2024 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/quantization/compressed_tensors/utils.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/utils.py
--- a/vllm/model_executor/layers/quantization/fbgemm_fp8.py
+++ b/vllm/model_executor/layers/quantization/fbgemm_fp8.py
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
--- a/vllm/model_executor/layers/quantization/gptq_marlin.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin.py
--- a/vllm/model_executor/layers/quantization/gptq_marlin_24.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin_24.py
--- a/vllm/model_executor/layers/quantization/kv_cache.py
+++ b/vllm/model_executor/layers/quantization/kv_cache.py
--- a/vllm/model_executor/layers/quantization/qqq.py
+++ b/vllm/model_executor/layers/quantization/qqq.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py
--- a/vllm/model_executor/layers/quantization/utils/quant_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/quant_utils.py
--- a/vllm/model_executor/layers/quantization/utils/w8a8_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/w8a8_utils.py
--- a/vllm/model_executor/layers/rejection_sampler.py
+++ b/vllm/model_executor/layers/rejection_sampler.py
--- a/vllm/model_executor/layers/rotary_embedding.py
+++ b/vllm/model_executor/layers/rotary_embedding.py
--- a/vllm/model_executor/layers/sampler.py
+++ b/vllm/model_executor/layers/sampler.py
--- a/vllm/model_executor/layers/spec_decode_base_sampler.py
+++ b/vllm/model_executor/layers/spec_decode_base_sampler.py
--- a/vllm/model_executor/model_loader/loader.py
+++ b/vllm/model_executor/model_loader/loader.py
--- a/vllm/model_executor/model_loader/weight_utils.py
+++ b/vllm/model_executor/model_loader/weight_utils.py