Eval bug: Getting memory critical errors when using --no-mmap with MoE models #14999
Description
Name and Version
After b6051, when running any MoE models (Qwen3-30B-A3B-2507-Instruct,Qwen3-235B-A22B-2507,Cogito-109B-MoE) with --no-mmap applied, I get errors like this:
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 = false)
srv log_server_r: request: GET /health 127.0.0.1 503
Memory critical error by agent node-0 (Agent handle: 0x4694bee0) on address 0x47934000. Reason: Memory in use.
I do not get these errors with non-MoE models like gemma-12b. I have enough VRAM (32GB) and RAM (256GB) to run these models and have run them successfully with --no-mmap in the past.
If mmap = TRUE, then the models load and run as expected.
May be related to #14990 ?
Operating systems
Linux
GGML backends
HIP
Hardware
Radeon V620
Models
No response
Problem description & steps to reproduce
Running llama-server via llama-swap
llama-server
--port ${PORT}
--flash-attn
-ctk q8_0
-ctv f16
-sm none -mg 0
--no-mmap
-m /mnt/models/unsloth/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL.gguf
-ot ".ffn_(up|down)_exps.=CPU"
-ngl 99
--temp 0.7
--min-p 0
--top-k 20
--top-p 0.8
--jinja
--ctx-size 250000
First Bad Commit
No response
Relevant log output
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon PRO V620, gfx1030 (0x1030), VMM: no, Wave Size: 32
Device 1: AMD Radeon (TM) Pro WX 3200 Series, gfx803 (0x803), VMM: no, Wave Size: 64
ggml_vulkan: Found 2 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon (TM) Pro WX 3200 Series (RADV POLARIS12) (radv) | uma: 0 | fp16: 0 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 0 | matrix cores: none
ggml_vulkan: 1 = AMD Radeon PRO V620 (RADV NAVI21) (radv) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 65536 | int dot: 1 | matrix cores: none
build: 6051 (a06ed5fe) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
system info: n_threads = 10, n_threads_batch = 10, total_threads = 18
system_info: n_threads = 10 (n_threads_batch = 10) / 18 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | FA_ALL_QUANTS = 1 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 5811, http threads: 17
main: loading model
srv load_model: loading model '/mnt/models/unsloth/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL.gguf'
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon PRO V620) - 30668 MiB free
llama_model_loader: loaded meta data with 45 key-value pairs and 579 tensors from /mnt/models/unsloth/Qwen3-30B-A3B-Instruct-2507-UD-Q6_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-Instruct-2507
llama_model_loader: - kv 3: general.version str = 2507
llama_model_loader: - kv 4: general.finetune str = Instruct
llama_model_loader: - kv 5: general.basename str = Qwen3-30B-A3B-Instruct-2507
llama_model_loader: - kv 6: general.quantized_by str = Unsloth
llama_model_loader: - kv 7: general.size_label str = 30B-A3B
llama_model_loader: - kv 8: general.license str = apache-2.0
llama_model_loader: - kv 9: general.license.link str = https://huggingface.co/Qwen/Qwen3-30B...
llama_model_loader: - kv 10: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 11: general.base_model.count u32 = 1
llama_model_loader: - kv 12: general.base_model.0.name str = Qwen3 30B A3B Instruct 2507
llama_model_loader: - kv 13: general.base_model.0.version str = 2507
llama_model_loader: - kv 14: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 15: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-30B...
llama_model_loader: - kv 16: general.tags arr[str,2] = ["unsloth", "text-generation"]
llama_model_loader: - kv 17: qwen3moe.block_count u32 = 48
llama_model_loader: - kv 18: qwen3moe.context_length u32 = 262144
llama_model_loader: - kv 19: qwen3moe.embedding_length u32 = 2048
llama_model_loader: - kv 20: qwen3moe.feed_forward_length u32 = 6144
llama_model_loader: - kv 21: qwen3moe.attention.head_count u32 = 32
llama_model_loader: - kv 22: qwen3moe.attention.head_count_kv u32 = 4
llama_model_loader: - kv 23: qwen3moe.rope.freq_base f32 = 10000000.000000
llama_model_loader: - kv 24: qwen3moe.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 25: qwen3moe.expert_used_count u32 = 8
llama_model_loader: - kv 26: qwen3moe.attention.key_length u32 = 128
llama_model_loader: - kv 27: qwen3moe.attention.value_length u32 = 128
llama_model_loader: - kv 28: qwen3moe.expert_count u32 = 128
llama_model_loader: - kv 29: qwen3moe.expert_feed_forward_length u32 = 768
llama_model_loader: - kv 30: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 31: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 32: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 33: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 34: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 35: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 36: tokenizer.ggml.padding_token_id u32 = 151654
llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 38: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 39: general.quantization_version u32 = 2
llama_model_loader: - kv 40: general.file_type u32 = 18
llama_model_loader: - kv 41: quantize.imatrix.file str = Qwen3-30B-A3B-Instruct-2507-GGUF/imat...
llama_model_loader: - kv 42: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-30B-A3B-Ins...
llama_model_loader: - kv 43: quantize.imatrix.entries_count u32 = 384
llama_model_loader: - kv 44: quantize.imatrix.chunks_count u32 = 693
llama_model_loader: - type f32: 241 tensors
llama_model_loader: - type q8_0: 166 tensors
llama_model_loader: - type q6_K: 172 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q6_K
print_info: file size = 24.53 GiB (6.90 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 = 262144
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 = 10000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 262144
print_info: rope_finetuned = unknown
print_info: model type = 30B.A3B
print_info: model params = 30.53 B
print_info: general.name = Qwen3-30B-A3B-Instruct-2507
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 = false)
srv log_server_r: request: GET /health 127.0.0.1 503
Memory critical error by agent node-0 (Agent handle: 0x4694bee0) on address 0x47934000. Reason: Memory in use.