search

PygmalionAI / aphrodite-engine

Large-scale LLM inference engine
https://aphrodite.pygmalion.chat
GNU Affero General Public License v3.0
1.15k stars 127 forks source link

[Usage]: Aphrodite Engine: KV Cache Context Length Issue with Quantized Models #812

Closed murtaza-nasir closed 1 week ago

murtaza-nasir commented 1 week ago

Your current environment

Collecting environment information...
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 24.04.1 LTS (x86_64)
GCC version: (Ubuntu 13.2.0-23ubuntu4) 13.2.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.39

Python version: 3.11.10 (main, Oct  3 2024, 07:29:13) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.8.0-48-generic-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.0.140
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 3090
GPU 1: NVIDIA GeForce RTX 3090
GPU 2: NVIDIA GeForce RTX 3090
GPU 3: NVIDIA GeForce RTX 3090
GPU 4: NVIDIA GeForce RTX 3090

Nvidia driver version: 550.120
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:                        43 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               64
On-line CPU(s) list:                  0-63
Vendor ID:                            AuthenticAMD
Model name:                           AMD EPYC 7532 32-Core Processor
CPU family:                           23
Model:                                49
Thread(s) per core:                   2
Core(s) per socket:                   32
Socket(s):                            1
Stepping:                             0
Frequency boost:                      enabled
CPU(s) scaling MHz:                   70%
CPU max MHz:                          2400.0000
CPU min MHz:                          1500.0000
BogoMIPS:                             4799.87
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sev sev_es
Virtualization:                       AMD-V
L1d cache:                            1 MiB (32 instances)
L1i cache:                            1 MiB (32 instances)
L2 cache:                             16 MiB (32 instances)
L3 cache:                             256 MiB (16 instances)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-63
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:        Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow:   Mitigation; Safe RET
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; Retpolines; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[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] numpy                     1.26.4                   pypi_0    pypi
[conda] nvidia-nccl-cu12          2.20.5                   pypi_0    pypi
[conda] pyzmq                     26.2.0                   pypi_0    pypi
[conda] torch                     2.4.0                    pypi_0    pypi
[conda] torchvision               0.19.0                   pypi_0    pypi
[conda] transformers              4.45.2                   pypi_0    pypi
[conda] triton                    3.0.0                    pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
Aphrodite Version: 0.6.3.post1
Aphrodite Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    GPU2    GPU3    GPU4    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      SYS     SYS     SYS     SYS     0-63    0               N/A
GPU1    SYS      X      SYS     SYS     SYS     0-63    0               N/A
GPU2    SYS     SYS      X      SYS     SYS     0-63    0               N/A
GPU3    SYS     SYS     SYS      X      PHB     0-63    0               N/A
GPU4    SYS     SYS     SYS     PHB      X      0-63    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

How would you like to use Aphrodite?

When running Qwen 2.5 (72B) AWQ with this command:

aphrodite run "/home/user/work/ml/text-generation-webui/models/Qwen_Qwen2.5-72B-Instruct-AWQ" \
-q "awq" --max-model-len 100000 --tensor-parallel-size 4 --gpu-memory-utilization 0.95 \
--served-model-name "localmodel-large" --port 5000 --host 0.0.0.0 --disable-log-requests

The engine forces down the context length:

Error:

ERROR: The model's max seq len (100000) is larger than the maximum number of tokens that can
be stored in KV cache (10176). Try increasing `gpu_memory_utilization`, setting
`--enable-chunked-prefill`, or `--kv-cache-dtype fp8`

Question: How can we achieve full context length with these models in Aphrodite?

murtaza-nasir commented 1 week ago

For anyone who may have the same issue, --enable-chunked-prefill solves this.