[Bug] Llama-3.2-1B-Instruct and InternVL2-1B does not supported kvin4, is that expected?

[zhulinJulia24]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

Llama-3.2-1B-Instruct does not supported kvin4, is that expected?

Reproduction

lmdeploy serve api_server /nvme/qa_test_models/meta-llama/Llama-3.2-1B-Instruct --session-len 8096 --server-port 23335 --tp 1 --quant-policy 4

Environment

sys.platform: linux
Python: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.8, V11.8.89
GCC: x86_64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 2.3.0+cu118
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX512
  - CUDA Runtime 11.8
  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_90,code=sm_90
  - CuDNN 8.7
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.3.0, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, 

TorchVision: 0.18.0+cu118
LMDeploy: 0.6.2+21f2866
transformers: 4.46.2
gradio: 5.5.0
fastapi: 0.115.4
pydantic: 2.9.2
triton: 2.3.0
NVIDIA Topology: 
	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	CPU Affinity	NUMA Affinity
GPU0	 X 	NV12	NV12	NV12	NV12	NV12	NV12	NV12	0-27,56-83	0
GPU1	NV12	 X 	NV12	NV12	NV12	NV12	NV12	NV12	0-27,56-83	0
GPU2	NV12	NV12	 X 	NV12	NV12	NV12	NV12	NV12	0-27,56-83	0
GPU3	NV12	NV12	NV12	 X 	NV12	NV12	NV12	NV12	0-27,56-83	0
GPU4	NV12	NV12	NV12	NV12	 X 	NV12	NV12	NV12	28-55,84-111	1
GPU5	NV12	NV12	NV12	NV12	NV12	 X 	NV12	NV12	28-55,84-111	1
GPU6	NV12	NV12	NV12	NV12	NV12	NV12	 X 	NV12	28-55,84-111	1
GPU7	NV12	NV12	NV12	NV12	NV12	NV12	NV12	 X 	28-55,84-111	1

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

Error traceback

Convert to turbomind format:   0%|          | 0/16 [00:00<?, ?it/s]
Convert to turbomind format:   6%|▋         | 1/16 [00:00<00:11,  1.36it/s]
Convert to turbomind format:  69%|██████▉   | 11/16 [00:00<00:00, 17.35it/s]
                                                                            
[WARNING] gemm_config.in is not found; using default GEMM algo
HINT:    Please open �[93m�[1mhttp://0.0.0.0:23335�[0m in a browser for detailed api usage!!!
HINT:    Please open �[93m�[1mhttp://0.0.0.0:23335�[0m in a browser for detailed api usage!!!
HINT:    Please open �[93m�[1mhttp://0.0.0.0:23335�[0m in a browser for detailed api usage!!!
INFO:     Started server process [96321]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:23335 (Press CTRL+C to quit)
INFO:     127.0.0.1:44438 - "GET /v1/models HTTP/1.1" 200 OK
terminate called after throwing an instance of 'std::runtime_error'
  what():  [TM][ERROR] CUDA runtime error: misaligned address /lmdeploy/src/turbomind/models/llama/LlamaBatch.cc:1292 

Aborted (core dumped)

[lvhan028]

@lzhangzz anything we need to do for kv int4 inference when the head_dim is 64?
@zhulinJulia24 Could you help quantizing llama-3.2-1b-instruct using lmdeploy lite auto_awq and verify its inference as well?

[zhulinJulia24]

@lzhangzz anything we need to do for kv int4 inference when the head_dim is 64? @zhulinJulia24 Could you help quantizing llama-3.2-1b-instruct using lmdeploy lite auto_awq and verify its inference as well?

same error for Llama-3.2-1B-Instruct-4bits and InternVL2-1B-4bits when use kvint4