Crash: Unable to get JIT kernel for brgemm. Params: M=31, N=31, K=128, str_a=1, str_b=1, brgemm_type=1, beta=0, a_trans=0, unroll_hint=1, lda=6144, ldb=31, ldc=31, config=0, b_vnni=0

[rohezal]

Describe the bug

By using float16 instead of bfloat16, it crashes with. Only bfloat16 works, which leads to very poor performance. This happens in pytorch 2.5.1 using your extension.

Works:
vllm serve ~/projects/webui/text-generation-webui/models/gpqt/ --dtype=bfloat16

Crashes :
vllm serve ~/projects/webui/text-generation-webui/models/gpqt/ --dtype=float16

Error:

ERROR 02-05 14:17:09 client.py:300] RuntimeError('Engine process (pid 15188) died.')```


https://github.com/vllm-project/vllm/issues/12778

### Versions


INFO 02-05 14:11:02 __init__.py:186] Automatically detected platform cpu.
Collecting environment information...
PyTorch version: 2.5.1+cpu
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 12.3.0-1ubuntu1~22.04) 12.3.0
Clang version: 14.0.0-1ubuntu1.1
CMake version: version 3.31.4
Libc version: glibc-2.35

Python version: 3.12.8 | packaged by Anaconda, Inc. | (main, Dec 11 2024, 16:31:09) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.8.0-52-generic-x86_64-with-glibc2.35
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
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):                               16
On-line CPU(s) list:                  0-15
Vendor ID:                            AuthenticAMD
Model name:                           AMD Ryzen Threadripper 1900X 8-Core Processor
CPU family:                           23
Model:                                1
Thread(s) per core:                   2
Core(s) per socket:                   8
Socket(s):                            1
Stepping:                             1
Frequency boost:                      enabled
CPU max MHz:                          3800,0000
CPU min MHz:                          2200,0000
BogoMIPS:                             7584.62
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 amd_dcm aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb hw_pstate ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt sha_ni xsaveopt xsavec xgetbv1 clzero irperf xsaveerptr arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif overflow_recov succor smca sev
L1d cache:                            256 KiB (8 instances)
L1i cache:                            512 KiB (8 instances)
L2 cache:                             4 MiB (8 instances)
L3 cache:                             16 MiB (2 instances)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-15
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 vulnerable
Vulnerability Spec rstack overflow:   Vulnerable: Safe RET, no microcode
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; STIBP disabled; 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] pyzmq==26.2.1
[pip3] torch==2.5.1+cpu
[pip3] torchaudio==2.5.1+cpu
[pip3] torchvision==0.20.1+cpu
[pip3] transformers==4.48.2
[conda] numpy                     1.26.4                   pypi_0    pypi
[conda] pyzmq                     26.2.1                   pypi_0    pypi
[conda] torch                     2.5.1+cpu                pypi_0    pypi
[conda] torchaudio                2.5.1+cpu                pypi_0    pypi
[conda] torchvision               0.20.1+cpu               pypi_0    pypi
[conda] transformers              4.48.2                   pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.7.2.dev36+g18016a5e
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
========================= ROCm System Management Interface =========================
============================= Weight between two GPUs ==============================
       GPU0         
GPU0   0            

============================== Hops between two GPUs ===============================
       GPU0         
GPU0   0            

============================ Link Type between two GPUs ============================
       GPU0         
GPU0   0            

==================================== Numa Nodes ====================================
GPU[0]		: (Topology) Numa Node: 0
GPU[0]		: (Topology) Numa Affinity: 4294967295
=============================== End of ROCm SMI Log ================================

NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1

[devpramod]

Hi @rohezal
I noticed that there is no IPEX under relevant libraries. Is it installed?