merge v0.4.1

99b471c2 · zhuwenwen · 1925d2e9 · 468d761b · 99b471c2 · 99b471c2
Commit 99b471c2 authored May 21, 2024 by zhuwenwen
20 changed files
--- a/vllm/model_executor/guided_decoding.py
+++ b/vllm/model_executor/guided_decoding.py
--- a/vllm/model_executor/guided_logits_processors.py
+++ b/vllm/model_executor/guided_logits_processors.py
--- a/vllm/model_executor/layers/activation.py
+++ b/vllm/model_executor/layers/activation.py
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json
--- a/vllm/model_executor/layers/fused_moe/fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe.py
--- a/vllm/model_executor/layers/layernorm.py
+++ b/vllm/model_executor/layers/layernorm.py
--- a/vllm/model_executor/layers/linear.py
+++ b/vllm/model_executor/layers/linear.py
--- a/vllm/model_executor/layers/logits_processor.py
+++ b/vllm/model_executor/layers/logits_processor.py
--- a/vllm/model_executor/layers/ops/sample.py
+++ b/vllm/model_executor/layers/ops/sample.py
--- a/vllm/model_executor/layers/quantization/__init__.py
+++ b/vllm/model_executor/layers/quantization/__init__.py
--- a/vllm/model_executor/layers/quantization/aqlm.py
+++ b/vllm/model_executor/layers/quantization/aqlm.py
--- a/vllm/model_executor/layers/quantization/awq.py
+++ b/vllm/model_executor/layers/quantization/awq.py
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
--- a/vllm/model_executor/layers/quantization/gptq.py
+++ b/vllm/model_executor/layers/quantization/gptq.py
--- a/vllm/model_executor/layers/quantization/marlin.py
+++ b/vllm/model_executor/layers/quantization/marlin.py
--- a/vllm/model_executor/layers/quantization/schema.py
+++ b/vllm/model_executor/layers/quantization/schema.py