[Bug]: FP8 KV Cache FLASHINFER AssertionError

[ScOut3R]

Your current environment

The output of `python env.py`

Collecting environment information...
/usr/local/lib/python3.10/dist-packages/aphrodite/connections.py:8: RuntimeWarning: Failed to read commit hash:
No module named 'aphrodite.commit_id'
from aphrodite.version import __version__ as APHRODITE_VERSION
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.1.90+-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA L4
Nvidia driver version: 550.90.07
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        46 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               4
On-line CPU(s) list:                  0-3
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) CPU @ 2.20GHz
CPU family:                           6
Model:                                85
Thread(s) per core:                   2
Core(s) per socket:                   2
Socket(s):                            1
Stepping:                             7
BogoMIPS:                             4400.39
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves arat avx512_vnni md_clear arch_capabilities
Hypervisor vendor:                    KVM
Virtualization type:                  full
L1d cache:                            64 KiB (2 instances)
L1i cache:                            64 KiB (2 instances)
L2 cache:                             2 MiB (2 instances)
L3 cache:                             38.5 MiB (1 instance)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-3
Vulnerability Gather data sampling:   Not affected
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Mitigation; Enhanced IBRS
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown

Versions of relevant libraries:
[pip3] flashinfer==0.1.4+cu121torch2.4
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] pyzmq==26.2.0
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.45.2
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
Aphrodite Version: 0.6.5
Aphrodite Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	X 	0-3	0		N/A

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

🐛 Describe the bug

Loading a static FP8 model with FP8 KV cache using the FLASHINFER attention backend results in the following error.

AssertionError: key/v_scale is not supported in FlashInfer.

However when I switch to FLASH_ATTENTION or Xformers I get the following warning.

WARNING:  Please use FlashInfer backend with FP8 KV Cache for better performance                                                                                                                    
by setting the environment variable APHRODITE_ATTENTION_BACKEND=FLASHINFER

Looks like FLASHINFER should be working, but it fails, or the warning is incorrect.

I tested this on vLLM 0.6.5 and FLASHINFER works.

[AlpinDale]

What FlashInfer version do you have installed?

[ScOut3R]

What FlashInfer version do you have installed?

I built a Docker image using the aphrodite-openai target from the Dockerfile at git tag v0.6.5.

[AlpinDale]

FlashInfer currently doesn't work with finetuned k/v scales. You'll need to use a checkpoint without the KV cache quantization.