suhai332
commented
8 months ago I've encountered the same issue. How should the KV cache be expanded?
Open caol64 opened 9 months ago
suhai332
commented
8 months ago I've encountered the same issue. How should the KV cache be expanded?
ZhaoCake
commented
8 months ago I've encountered the same issue. How should the KV cache be expanded?
ZhaoCake
commented
8 months ago Guys, I find the way to increase KV Cache. As you know KV Cache can be seen as a part of prompt, we can just increase the --ctx-size parameter, which is also called -c
-c N, --ctx-size N
Set the size of the prompt context. A larger context size helps
the model to better comprehend and generate responses for longer
input or conversations. The LLaMA models were built with a con‐
text of 2048, which yields the best results on longer input / in‐
ference.
- 0 = loaded automatically from model
Default: 512The final KV Cache is related to your quantitize for the model. For me,
sh ./Qwen-7B-Chat-q4_0.llamafile -c 4096Error:
[1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 256 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 128 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 64 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 32 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 16 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 8 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 4 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 2 [1707364943] update_slots : failed to find free space in the KV cache, retrying with smaller n_batch = 1 [1707364943] update_slots : failed to decode the batch, n_batch = 1, ret = 1Environment:
Apple Metal GPU support successfully loaded {"timestamp":1707365237,"level":"INFO","function":"server_cli","line":2457,"message":"build info","build":1500,"commit":"a30b324"} {"timestamp":1707365237,"level":"INFO","function":"server_cli","line":2460,"message":"system info","n_threads":5,"n_threads_batch":-1,"total_threads":10,"system_info":"AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | "} [1707365237] llama server listening at http://127.0.0.1:8080 {"timestamp":1707365237,"level":"INFO","function":"server_cli","line":2594,"message":"HTTP server listening","port":"8080","hostname":"127.0.0.1"} llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from ./mistral-7b-instruct-v0.2.Q8_0.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 = llama llama_model_loader: - kv 1: general.name str = mistralai_mistral-7b-instruct-v0.2 llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 11: general.file_type u32 = 7 llama_model_loader: - kv 12: tokenizer.ggml.model str = llama llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 22: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 23: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q8_0: 226 tensors llm_load_vocab: special tokens definition check successful ( 259/32000 ). llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 32000 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 1000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 32768 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: model type = 7B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 7.24 B llm_load_print_meta: model size = 7.17 GiB (8.50 BPW) llm_load_print_meta: general.name = mistralai_mistral-7b-instruct-v0.2 llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 2 '</s>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: PAD token = 0 '<unk>' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_tensors: ggml ctx size = 0.22 MiB ggml_backend_metal_buffer_from_ptr: allocated buffer, size = 7205.84 MiB, ( 7205.91 / 21845.34) llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: Metal buffer size = 7205.84 MiB llm_load_tensors: CPU buffer size = 132.81 MiB .................................................................................................. llama_new_context_with_model: n_ctx = 512 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M1 Pro ggml_metal_init: picking default device: Apple M1 Pro ggml_metal_init: default.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/var/folders/vy/qgmfv1b9063_xfqfdglynmm00000gn/T/.llamafile/ggml-metal.metal' ggml_metal_init: GPU name: Apple M1 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple7 (1007) ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003) ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001) ggml_metal_init: simdgroup reduction support = true ggml_metal_init: simdgroup matrix mul. support = true ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 22906.50 MB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 64.00 MiB, ( 7271.47 / 21845.34) llama_kv_cache_init: Metal KV buffer size = 64.00 MiB llama_new_context_with_model: KV self size = 64.00 MiB, K (f16): 32.00 MiB, V (f16): 32.00 MiB llama_new_context_with_model: CPU input buffer size = 9.01 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 7271.48 / 21845.34) ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 80.31 MiB, ( 7351.78 / 21845.34) llama_new_context_with_model: Metal compute buffer size = 80.30 MiB llama_new_context_with_model: CPU compute buffer size = 8.80 MiB llama_new_context_with_model: graph splits (measure): 3 [1707365237] warming up the model with an empty run [1707365238] Available slots: [1707365238] -> Slot 0 - max context: 512 {"timestamp":1707365238,"level":"INFO","function":"server_cli","line":2615,"message":"model loaded"} opening browser tab... (pass --nobrowser to disable) [1707365238] all slots are idle and system prompt is empty, clear the KV cache
tlkahn
commented
6 months ago Thanks for the hint! It works well so far. 😺
Error:
Environment: