Open
Description
Name and Version
root@llama-0:/app# ./llama-server --version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon RX 7900 XT, gfx1100 (0x1100), VMM: no, Wave Size: 32
load_backend: loaded ROCm backend from /app/libggml-hip.so
load_backend: loaded CPU backend from /app/libggml-cpu-icelake.so
version: 5662 (fb85a28)
built with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
libllama (core library), llama-cli, llama-server
Command line
/app/llama-server --port ${PORT}
-m /data/Qwen3-30B-A3B-UD-Q4_K_XL.gguf
-ngl 99 -t 6
--cache-type-k q8_0
--cache-type-v q8_0
--ctx-size 32768
--flash-attnProblem description & steps to reproduce
- Build llama.cpp with ROCm 6.4
- Attempt to load large model (e.g
Qwen3-30B-A3B-UD-Q4_K_XL.gguf) - llama.cpp reports it is unable to allocate buffer
First Bad Commit
No response
Relevant log output
# During build
In file included from /app/ggml/src/ggml-cuda/acc.cu:1:
In file included from /app/ggml/src/ggml-cuda/acc.cuh:1:
/app/ggml/src/ggml-cuda/common.cuh:266:12: warning: macro '__AMDGCN_WAVEFRONT_SIZE' has been marked as deprecated: compile-time-constant access to the wavefront size will be removed in a future release [-Wdeprecated-pragma]
266 | return __AMDGCN_WAVEFRONT_SIZE;
| ^
<built-in>:891:139: note: macro marked 'deprecated' here
891 | #pragma clang deprecated(__AMDGCN_WAVEFRONT_SIZE, "compile-time-constant access to the wavefront size will be removed in a future release")
| ^
# Loading model (qwen3:30b, Q4)
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon RX 7900 XT, gfx1100 (0x1100), VMM: no, Wave Size: 32
load_backend: loaded ROCm backend from /app/libggml-hip.so
load_backend: loaded CPU backend from /app/libggml-cpu-icelake.so
build: 5662 (fb85a288) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
system info: n_threads = 6, n_threads_batch = 6, total_threads = 8
system_info: n_threads = 6 (n_threads_batch = 6) / 8 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 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: 7
main: loading model
srv load_model: loading model '/data/Qwen3-30B-A3B-UD-Q4_K_XL.gguf'
llama_model_load_from_file_impl: using device ROCm0 (Radeon RX 7900 XT) - 20420 MiB free
llama_model_loader: loaded meta data with 35 key-value pairs and 579 tensors from /data/Qwen3-30B-A3B-UD-Q4_K_XL.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 = qwen3moe
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen3-30B-A3B
llama_model_loader: - kv 3: general.basename str = Qwen3-30B-A3B
llama_model_loader: - kv 4: general.quantized_by str = Unsloth
llama_model_loader: - kv 5: general.size_label str = 30B-A3B
llama_model_loader: - kv 6: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 7: qwen3moe.block_count u32 = 48
llama_model_loader: - kv 8: qwen3moe.context_length u32 = 40960
llama_model_loader: - kv 9: qwen3moe.embedding_length u32 = 2048
llama_model_loader: - kv 10: qwen3moe.feed_forward_length u32 = 6144
llama_model_loader: - kv 11: qwen3moe.attention.head_count u32 = 32
llama_model_loader: - kv 12: qwen3moe.attention.head_count_kv u32 = 4
llama_model_loader: - kv 13: qwen3moe.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 14: qwen3moe.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 15: qwen3moe.expert_used_count u32 = 8
llama_model_loader: - kv 16: qwen3moe.attention.key_length u32 = 128
llama_model_loader: - kv 17: qwen3moe.attention.value_length u32 = 128
llama_model_loader: - kv 18: qwen3moe.expert_count u32 = 128
llama_model_loader: - kv 19: qwen3moe.expert_feed_forward_length u32 = 768
llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 21: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 25: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 26: tokenizer.ggml.padding_token_id u32 = 151654
llama_model_loader: - kv 27: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 28: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 29: general.quantization_version u32 = 2
llama_model_loader: - kv 30: general.file_type u32 = 15
llama_model_loader: - kv 31: quantize.imatrix.file str = Qwen3-30B-A3B-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv 32: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-30B-A3B.txt
llama_model_loader: - kv 33: quantize.imatrix.entries_count i32 = 384
llama_model_loader: - kv 34: quantize.imatrix.chunks_count i32 = 685
llama_model_loader: - type f32: 241 tensors
llama_model_loader: - type q4_K: 290 tensors
llama_model_loader: - type q5_K: 37 tensors
llama_model_loader: - type q6_K: 11 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 16.49 GiB (4.64 BPW)
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3moe
print_info: vocab_only = 0
print_info: n_ctx_train = 40960
print_info: n_embd = 2048
print_info: n_layer = 48
print_info: n_head = 32
print_info: n_head_kv = 4
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 8
print_info: n_embd_k_gqa = 512
print_info: n_embd_v_gqa = 512
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 = 6144
print_info: n_expert = 128
print_info: n_expert_used = 8
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 40960
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 30B.A3B
print_info: model params = 30.53 B
print_info: general.name = Qwen3-30B-A3B
print_info: n_ff_exp = 768
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 11 ','
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151654 '<|vision_pad|>'
print_info: LF token = 198 'Ċ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
ggml_backend_cuda_buffer_type_alloc_buffer: allocating 16722.37 MiB on device 0: cudaMalloc failed: out of memory
alloc_tensor_range: failed to allocate ROCm0 buffer of size 17534674944
llama_model_load: error loading model: unable to allocate ROCm0 buffer
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '/data/Qwen3-30B-A3B-UD-Q4_K_XL.gguf'
srv load_model: failed to load model, '/data/Qwen3-30B-A3B-UD-Q4_K_XL.gguf'
srv operator(): operator(): cleaning up before exit...
main: exiting due to model loading error