我自己编译的llama.cpp. 代码仓库代码太老了不支持deepseek

cmake -S . -B build -DGGML_HIP=1 -DCMAKE_POSITION_INDEPENDENT_CODE=on -DCMAKE_BUILD_TYPE=Release -DLLAMA_SERVER_VERBOSE=off -DCMAKE_C_COMPILER=/opt/dtk/llvm/bin/clang -DCMAKE_CXX_COMPILER=/opt/dtk/llvm/bin/clang++ -DAMDGPU_TARGETS=gfx928 -DGPU_TARGETS=gfx928 
# 如下这段执行不成功
for f in `ag xhip build -l`
do

   sed -i 's/^\(C_FLAGS.*\) -xhip --cuda-gpu-arch=gfx928\(.*\)/\1 --gpu-max-threads-per-block=1024 \2/g' $f
   sed -i 's/^\(CXX_FLAGS.*\)/\1 --gpu-max-threads-per-block=1024/g' $f
done
export LIBRARY_PATH=/opt/dtk/llvm/lib/clang/15.0.0/lib/linux/:$LIBRARY_PATH
cmake --build build --config Release -- -j 128

能否请更新一下llama.cpp用来支持量化GGUF模型,还是说有限制只能支持Q4/Q8量化? 因为我用的是unsloth的UD-Q2_K_XL量化. 谢谢各位社区大佬

./llama-server -m /srv/disk1/models/unsloth/DeepSeek-V3-0324-GGUF/UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00001-of-00006.gguf --host 0.0.0.0 -ngl 999
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 8 ROCm devices:
  Device 0: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
  Device 1: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
  Device 2: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
  Device 3: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
  Device 4: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
  Device 5: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
  Device 6: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
  Device 7: K100_AI, gfx928:sramecc+:xnack- (0x928), VMM: no, Wave Size: 64
build: 6210 (a094f381) with clang version 15.0.0 for x86_64-unknown-linux-gnu
system info: n_threads = 128, n_threads_batch = 128, total_threads = 255

system_info: n_threads = 128 (n_threads_batch = 128) / 255 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 

main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8080, http threads: 254
main: loading model
srv    load_model: loading model '/srv/disk1/models/unsloth/DeepSeek-V3-0324-GGUF/UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00001-of-00006.gguf'
llama_model_load_from_file_impl: using device ROCm0 (K100_AI) - 64749 MiB free
llama_model_load_from_file_impl: using device ROCm1 (K100_AI) - 64749 MiB free
llama_model_load_from_file_impl: using device ROCm2 (K100_AI) - 64749 MiB free
llama_model_load_from_file_impl: using device ROCm3 (K100_AI) - 64749 MiB free
llama_model_load_from_file_impl: using device ROCm4 (K100_AI) - 64749 MiB free
llama_model_load_from_file_impl: using device ROCm5 (K100_AI) - 64749 MiB free
llama_model_load_from_file_impl: using device ROCm6 (K100_AI) - 64749 MiB free
llama_model_load_from_file_impl: using device ROCm7 (K100_AI) - 64749 MiB free
llama_model_loader: additional 5 GGUFs metadata loaded.
llama_model_loader: loaded meta data with 49 key-value pairs and 1025 tensors from /srv/disk1/models/unsloth/DeepSeek-V3-0324-GGUF/UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00001-of-00006.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = deepseek2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = DeepSeek V3 0324 BF16
llama_model_loader: - kv   3:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   4:                         general.size_label str              = 256x20B
llama_model_loader: - kv   5:                            general.license str              = mit
llama_model_loader: - kv   6:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   7:                      deepseek2.block_count u32              = 61
llama_model_loader: - kv   8:                   deepseek2.context_length u32              = 163840
llama_model_loader: - kv   9:                 deepseek2.embedding_length u32              = 7168
llama_model_loader: - kv  10:              deepseek2.feed_forward_length u32              = 18432
llama_model_loader: - kv  11:             deepseek2.attention.head_count u32              = 128
llama_model_loader: - kv  12:          deepseek2.attention.head_count_kv u32              = 128
llama_model_loader: - kv  13:                   deepseek2.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  14: deepseek2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  15:                deepseek2.expert_used_count u32              = 8
llama_model_loader: - kv  16:        deepseek2.leading_dense_block_count u32              = 3
llama_model_loader: - kv  17:                       deepseek2.vocab_size u32              = 129280
llama_model_loader: - kv  18:            deepseek2.attention.q_lora_rank u32              = 1536
llama_model_loader: - kv  19:           deepseek2.attention.kv_lora_rank u32              = 512
llama_model_loader: - kv  20:             deepseek2.attention.key_length u32              = 192
llama_model_loader: - kv  21:           deepseek2.attention.value_length u32              = 128
llama_model_loader: - kv  22:       deepseek2.expert_feed_forward_length u32              = 2048
llama_model_loader: - kv  23:                     deepseek2.expert_count u32              = 256
llama_model_loader: - kv  24:              deepseek2.expert_shared_count u32              = 1
llama_model_loader: - kv  25:             deepseek2.expert_weights_scale f32              = 2.500000
llama_model_loader: - kv  26:              deepseek2.expert_weights_norm bool             = true
llama_model_loader: - kv  27:               deepseek2.expert_gating_func u32              = 2
llama_model_loader: - kv  28:             deepseek2.rope.dimension_count u32              = 64
llama_model_loader: - kv  29:                deepseek2.rope.scaling.type str              = yarn
llama_model_loader: - kv  30:              deepseek2.rope.scaling.factor f32              = 40.000000
llama_model_loader: - kv  31: deepseek2.rope.scaling.original_context_length u32              = 4096
llama_model_loader: - kv  32: deepseek2.rope.scaling.yarn_log_multiplier f32              = 0.100000
llama_model_loader: - kv  33:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  34:                         tokenizer.ggml.pre str              = deepseek-v3
llama_model_loader: - kv  35:                      tokenizer.ggml.tokens arr[str,129280]  = ["<｜begin▁of▁sentence｜>", "<...
llama_model_loader: - kv  36:                  tokenizer.ggml.token_type arr[i32,129280]  = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  37:                      tokenizer.ggml.merges arr[str,127741]  = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e...
llama_model_loader: - kv  38:                tokenizer.ggml.bos_token_id u32              = 0
llama_model_loader: - kv  39:                tokenizer.ggml.eos_token_id u32              = 1
llama_model_loader: - kv  40:            tokenizer.ggml.padding_token_id u32              = 1
llama_model_loader: - kv  41:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  42:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  43:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  44:               general.quantization_version u32              = 2
llama_model_loader: - kv  45:                          general.file_type u32              = 10
llama_model_loader: - kv  46:                                   split.no u16              = 0
llama_model_loader: - kv  47:                        split.tensors.count i32              = 1025
llama_model_loader: - kv  48:                                split.count u16              = 6
llama_model_loader: - type  f32:  361 tensors
llama_model_loader: - type q2_K:  116 tensors
llama_model_loader: - type q3_K:   58 tensors
llama_model_loader: - type q4_K:  306 tensors
llama_model_loader: - type q6_K:  184 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q2_K - Medium
print_info: file size   = 230.59 GiB (2.95 BPW) 
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: printing all EOG tokens:
load:   - 1 ('<｜end▁of▁sentence｜>')
load: special tokens cache size = 818
load: token to piece cache size = 0.8223 MB
print_info: arch             = deepseek2
print_info: vocab_only       = 0
print_info: n_ctx_train      = 163840
print_info: n_embd           = 7168
print_info: n_layer          = 61
print_info: n_head           = 128
print_info: n_head_kv        = 128
print_info: n_rot            = 64
print_info: n_swa            = 0
print_info: is_swa_any       = 0
print_info: n_embd_head_k    = 192
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 1
print_info: n_embd_k_gqa     = 24576
print_info: n_embd_v_gqa     = 16384
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 18432
print_info: n_expert         = 256
print_info: n_expert_used    = 8
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 0
print_info: rope scaling     = yarn
print_info: freq_base_train  = 10000.0
print_info: freq_scale_train = 0.025
print_info: n_ctx_orig_yarn  = 4096
print_info: rope_finetuned   = unknown
print_info: model type       = 671B
print_info: model params     = 671.03 B
print_info: general.name     = DeepSeek V3 0324 BF16
print_info: n_layer_dense_lead   = 3
print_info: n_lora_q             = 1536
print_info: n_lora_kv            = 512
print_info: n_embd_head_k_mla    = 0
print_info: n_embd_head_v_mla    = 0
print_info: n_ff_exp             = 2048
print_info: n_expert_shared      = 1
print_info: expert_weights_scale = 2.5
print_info: expert_weights_norm  = 1
print_info: expert_gating_func   = sigmoid
print_info: rope_yarn_log_mul    = 0.1000
print_info: vocab type       = BPE
print_info: n_vocab          = 129280
print_info: n_merges         = 127741
print_info: BOS token        = 0 '<｜begin▁of▁sentence｜>'
print_info: EOS token        = 1 '<｜end▁of▁sentence｜>'
print_info: EOT token        = 1 '<｜end▁of▁sentence｜>'
print_info: PAD token        = 1 '<｜end▁of▁sentence｜>'
print_info: LF token         = 201 'Ċ'
print_info: FIM PRE token    = 128801 '<｜fim▁begin｜>'
print_info: FIM SUF token    = 128800 '<｜fim▁hole｜>'
print_info: FIM MID token    = 128802 '<｜fim▁end｜>'
print_info: EOG token        = 1 '<｜end▁of▁sentence｜>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 61 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 62/62 layers to GPU
load_tensors:   CPU_Mapped model buffer size =   497.11 MiB
load_tensors:        ROCm0 model buffer size = 21211.09 MiB
load_tensors:        ROCm1 model buffer size = 32254.47 MiB
load_tensors:        ROCm2 model buffer size = 32254.47 MiB
load_tensors:        ROCm3 model buffer size = 28222.66 MiB
load_tensors:        ROCm4 model buffer size = 32254.47 MiB
load_tensors:        ROCm5 model buffer size = 32254.47 MiB
load_tensors:        ROCm6 model buffer size = 32254.47 MiB
load_tensors:        ROCm7 model buffer size = 24915.83 MiB
....................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: kv_unified    = false
llama_context: freq_base     = 10000.0
llama_context: freq_scale    = 0.025
llama_context: n_ctx_per_seq (4096) < n_ctx_train (163840) -- the full capacity of the model will not be utilized
llama_context:  ROCm_Host  output buffer size =     0.49 MiB
llama_kv_cache_unified:      ROCm0 KV buffer size =  2560.00 MiB
llama_kv_cache_unified:      ROCm1 KV buffer size =  2560.00 MiB
llama_kv_cache_unified:      ROCm2 KV buffer size =  2560.00 MiB
llama_kv_cache_unified:      ROCm3 KV buffer size =  2240.00 MiB
llama_kv_cache_unified:      ROCm4 KV buffer size =  2560.00 MiB
llama_kv_cache_unified:      ROCm5 KV buffer size =  2560.00 MiB
llama_kv_cache_unified:      ROCm6 KV buffer size =  2560.00 MiB
llama_kv_cache_unified:      ROCm7 KV buffer size =  1920.00 MiB
llama_kv_cache_unified: size = 19520.00 MiB (  4096 cells,  61 layers,  1/1 seqs), K (f16): 11712.00 MiB, V (f16): 7808.00 MiB
llama_context: pipeline parallelism enabled (n_copies=4)
llama_context:      ROCm0 compute buffer size =  1522.02 MiB
llama_context:      ROCm1 compute buffer size =  1522.02 MiB
llama_context:      ROCm2 compute buffer size =  1522.02 MiB
llama_context:      ROCm3 compute buffer size =  1522.02 MiB
llama_context:      ROCm4 compute buffer size =  1522.02 MiB
llama_context:      ROCm5 compute buffer size =  1522.02 MiB
llama_context:      ROCm6 compute buffer size =  1522.02 MiB
llama_context:      ROCm7 compute buffer size =  1522.03 MiB
llama_context:  ROCm_Host compute buffer size =   302.04 MiB
llama_context: graph nodes  = 4845
llama_context: graph splits = 9
common_init_from_params: added <｜end▁of▁sentence｜> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
/srv/disk2/llama.cpp/ggml/src/ggml-cuda/template-instances/../mmq.cuh:3145: ERROR: HIP kernel mul_mat_q has no device code compatible with HIP arch 1300.
Callback: Queue 0x7f0a9b600000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016
>>>>>>>> KERNEL VMFault !!!! <<<<<<

>>>>>>>> PID: 176353, SIGNAL: 0 !!!! <<<<<<

===========================================================================================
=========> HOSTQUEUE <0x40336a0>: VMFault HSA QUEUE ANALYSIS <=========
HOSTQUEUE <0x40336a0>: get hsa queue W/R ptr: write index: 142, read index: 139

HOSTQUEUE <0x40336a0>: >>>>>>>> DUMP AQL 0x7f12f3084000 PACKET WITH INDEX 139 <<<<<<<<<
HOSTQUEUE <0x40336a0>: >>>>>>>> MATCH KERNEL COMMAND <<<<<<<<<
HOSTQUEUE <0x40336a0>: header: 0xb02
HOSTQUEUE <0x40336a0>: setup: 3
HOSTQUEUE <0x40336a0>: workgroup: x:64, y:8, z:1
HOSTQUEUE <0x40336a0>: grid: x:7680, y:8, z:1
HOSTQUEUE <0x40336a0>: group_segment_size: 63808
HOSTQUEUE <0x40336a0>: private_segment_size: 160
HOSTQUEUE <0x40336a0>: completion_signal: 0x0
HOSTQUEUE <0x40336a0>: kernel_object: 0x7f0255a1a240
HOSTQUEUE <0x40336a0>: device id: 0

HOSTQUEUE <0x40336a0>: >>>>>>>> FIND MATCH KERNEL DETAILS <<<<<<<<<
HOSTQUEUE <0x40336a0>: kernel name: _ZL9mul_mat_qIL9ggml_type10ELi80ELb0EEvPKcPKiS4_S4_PfS5_iiiiiiiiiiiiiiii
HOSTQUEUE <0x40336a0>: >>>>>>>> DUMP KERNEL ARGS: size: 168 <<<<<<<<<

00 fc 69 c8 cb 7e 00 00 00 00 40 56 02 7f 00 00 
00 08 00 57 02 7f 00 00 00 10 00 57 02 7f 00 00 
00 60 38 1d 05 7f 00 00 00 00 c0 55 02 7f 00 00 
00 1c 00 00 00 08 00 00 00 02 00 00 1c 00 00 00 
00 02 00 00 00 08 00 00 01 00 00 00 00 01 00 00 
00 e0 00 00 e0 07 00 00 00 00 08 00 01 00 00 00 
01 00 00 00 00 00 e0 00 c0 0f 00 00 00 00 10 00 
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 
00 00 00 00 00 00 00 00 00 00 40 54 02 7f 00 00 
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 
00 00 00 00 00 00 00 00 

HOSTQUEUE <0x40336a0>: >>>>>>>> DUMP KERNEL ARGS PTR INFO <<<<<<<<<
HOSTQUEUE <0x40336a0>: ptr arg index: 0, ptr: 0x7ecbc869fc00
HOSTQUEUE <0x40336a0>: origin ptr: 0x7ecb7fa00000, size byte: 22241444864
HOSTQUEUE <0x40336a0>: ptr arg index: 1, ptr: 0x7f0256400000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0256400000, size byte: 4354560
HOSTQUEUE <0x40336a0>: ptr arg index: 2, ptr: 0x7f0257000800
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0257000000, size byte: 17152
HOSTQUEUE <0x40336a0>: ptr arg index: 3, ptr: 0x7f0257001000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0257000000, size byte: 17152
HOSTQUEUE <0x40336a0>: ptr arg index: 4, ptr: 0x7f051d386000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0505e00000, size byte: 1595957248
HOSTQUEUE <0x40336a0>: ptr arg index: 5, ptr: 0x7f0255c00000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0255c00000, size byte: 5160960
HOSTQUEUE <0x40336a0>: ptr arg index: 17, ptr: 0x7f0254400000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0254400000, size byte: 19776056

HOSTQUEUE <0x40336a0>: >>>>>>>> DUMP AQL 0x7f12f3084000 PACKET WITH INDEX 140 <<<<<<<<<
HOSTQUEUE <0x40336a0>: >>>>>>>> MATCH KERNEL COMMAND <<<<<<<<<
HOSTQUEUE <0x40336a0>: header: 0xb02
HOSTQUEUE <0x40336a0>: setup: 3
HOSTQUEUE <0x40336a0>: workgroup: x:64, y:8, z:1
HOSTQUEUE <0x40336a0>: grid: x:7680, y:8, z:1
HOSTQUEUE <0x40336a0>: group_segment_size: 320
HOSTQUEUE <0x40336a0>: private_segment_size: 260
HOSTQUEUE <0x40336a0>: completion_signal: 0x0
HOSTQUEUE <0x40336a0>: kernel_object: 0x7f0255a1a2c0
HOSTQUEUE <0x40336a0>: device id: 0

HOSTQUEUE <0x40336a0>: >>>>>>>> FIND MATCH KERNEL DETAILS <<<<<<<<<
HOSTQUEUE <0x40336a0>: kernel name: _ZL24mul_mat_q_stream_k_fixupIL9ggml_type10ELi80ELb0EEvPKiS2_PfPKfiiiiiiii
HOSTQUEUE <0x40336a0>: >>>>>>>> DUMP KERNEL ARGS: size: 64 <<<<<<<<<

00 08 00 57 02 7f 00 00 00 10 00 57 02 7f 00 00 
00 60 38 1d 05 7f 00 00 00 00 c0 55 02 7f 00 00 
00 1c 00 00 00 08 00 00 00 02 00 00 00 08 00 00 
00 01 00 00 00 00 08 00 01 00 00 00 00 00 10 00 

HOSTQUEUE <0x40336a0>: >>>>>>>> DUMP KERNEL ARGS PTR INFO <<<<<<<<<
HOSTQUEUE <0x40336a0>: ptr arg index: 0, ptr: 0x7f0257000800
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0257000000, size byte: 17152
HOSTQUEUE <0x40336a0>: ptr arg index: 1, ptr: 0x7f0257001000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0257000000, size byte: 17152
HOSTQUEUE <0x40336a0>: ptr arg index: 2, ptr: 0x7f051d386000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0505e00000, size byte: 1595957248
HOSTQUEUE <0x40336a0>: ptr arg index: 3, ptr: 0x7f0255c00000
HOSTQUEUE <0x40336a0>: origin ptr: 0x7f0255c00000, size byte: 5160960

HOSTQUEUE <0x40336a0>: >>>>>>>> DUMP AQL 0x7f12f3084000 PACKET WITH INDEX 141 <<<<<<<<<
HOSTQUEUE <0x40336a0>: >>>>>>>> MATCH BARRIER AND COMMAND <<<<<<<<<
HOSTQUEUE <0x40336a0>: header: 0x1503
HOSTQUEUE <0x40336a0>: dep_signal[0]: 0x0
HOSTQUEUE <0x40336a0>: dep_signal[1]: 0x0
HOSTQUEUE <0x40336a0>: dep_signal[2]: 0x0
HOSTQUEUE <0x40336a0>: dep_signal[3]: 0x0
HOSTQUEUE <0x40336a0>: dep_signal[4]: 0x0
HOSTQUEUE <0x40336a0>: completion_signal: 0x7f12f44ea500



===========================================================================================
=========> HOSTQUEUE <0x6169490>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x676de00>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x405ed90>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6554940>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6773670>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x3f66080>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x659f440>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x698ce20>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x3f667a0>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6a922b0>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x65ea2d0>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x3f6b750>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6635160>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6b97720>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x4058970>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6c9cbb0>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6680150>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6da2290>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x403a0e0>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x66cb140>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x404de60>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6ea77f0>: VMFault HSA QUEUE ANALYSIS <=========

===========================================================================================
=========> HOSTQUEUE <0x6716110>: VMFault HSA QUEUE ANALYSIS <=========

>>>>>>>> KERNEL VMFault Analysis END !!!! <<<<<<


>>>>>>>> KERNEL VMFault Analysis END !!!! <<<<<<

Aborted (core dumped)