sgl-project/sglang
Documented errors, page 31 of 32. Back to sgl-project/sglang
| Code / Message | Type | Severity | Tags |
|---|---|---|---|
| Currently DFLASH speculative decoding only supports pp_size… | validation | error | speculative-decoding, dflash, pipeline-parallel, server-args |
| Currently DSpark speculative decoding only supports pp_size… | validation | error | speculative-decoding, dspark, pipeline-parallel |
| DFLASH speculative decoding requires setting… | validation | error | speculative-decoding, dflash, draft-model, missing-argument |
| hpc_ops backend can only be used with non-MLA models. | validation | error | attention-backend, hpc-ops, mla, model-arch-mismatch, npu, sglang |
| lora_path list length | validation | error | sglang, lora, batching, input-validation |
| Sequence length exceeds the maximum . | validation | error | clip, sequence-length, input-validation |
| T2I adapter residuals are not supported by Hunyuan3D. | validation | error | t2i-adapter, unsupported-argument, hunyuan3d |
| (empty data payload) | validation | error | base64, data-uri, empty-payload, validation |
| file URI host must be local, got | validation | error | file-uri, minimax-h3, material-uri |
| invalid IPv6 address | validation | error | ipv6, distributed, network, validation |
| Unsupported Mobius layer type | exception | error | layer-type, checkpoint-compat, model-config |
| Unsupported V4 paged host layout/backend | validation | error | sglang, hicache, io-backend, layout, unsupported |
| kv-canary: scatter_req_token_ids pool_out must be int32, got | validation | error | kv-cache, dtype-validation, torch |
| LoRA is not enabled. Please set `--enable-lora` to enable… | http | error | lora, config, http-api |
| prompt event payload must be a non-empty string | validation | error | realtime, event-validation, prompt, empty-value |
| Hugging Face weight URL has no model repo | validation | error | huggingface, weights, malformed-url |
| items must be provided | validation | error | scoring, missing-argument, validation |
| Unsupported TP style | validation | error | tensor-parallel, transformers-backend, tp-plan |
| cu_seqlens_k tensor must be Int32 | validation | error | cuda, dtype, flash-attention, varlen, int32 |
| FlashKDAKernel only supports prefill (extend) | exception | error | sglang, flashkda, kda, decode, not-implemented |
| must be a scalar tensor, got shape | validation | error | mla, quantization, scale-validation, shape |
| reasoning_effort must not be a boolean | validation | error | openai-api, reasoning-effort, type-error |
| keyframe denoising requires one encoded keyframe per… | validation | error | minimax-h3, keyframe, cardinality, type-validation |
| Length mismatch: lora_nicknames has | validation | error | lora, argument-validation, length-mismatch |
| --sidecar must not be empty. | validation | error | grpc, sidecar, config-validation |
| Unsupported activation. Only silu is supported for now. | validation | critical | activation, config-validation, bailing-moe |
| Unsupported parallel style type | validation | error | type-validation, tensor-parallel, transformers-backend |
| extra_config['ssd_io_backend'] must be one of: posix… | validation | error | umbp, config-validation, io-backend |
| max_seqlen must be positive, got | validation | error | cuda-graph, kimi-k3, config-validation |
| Either input_ids or inputs_embeds must be provided. | validation | error | clip, input-validation, embeddings |
| Invalid grammar backend | validation | error | grammar, configuration, startup |
| kv-canary: scatter_req_token_ids req_pool_indices must be… | validation | error | kv-cache, dtype-validation, torch |
| Component residency selector cannot be empty | validation | error | config, component-residency, parsing, empty-value |
| must be on q's device , got | validation | error | mla, quantization, multi-gpu, device-mismatch |
| has unknown fields | validation | error | minimax-h3, conditions, unknown-fields, schema |
| kv-canary: length must be >= , got | validation | error | kv-canary, length-mismatch, lut |
| kv-canary: must be 1-D, got shape | validation | error | kv-canary, shape, validation |
| You have to specify pixel_values or pixel_embeds | exception | error | multimodal, vision, missing-input |
| Function tools must include a name. | validation | error | responses-api, tool-calling, validation, sglang |
| is empty | validation | error | minimax-h3, empty-file, material-validation |
| MiniMax H3 media material is invalid | validation | error | minimax-h3, ffprobe, ffmpeg-missing, media-validation |
| norm_type must be one of "layer" and "rms" | validation | error | enum, norm, validation |
| Unknown CacheAgnostic Policy | validation | error | scheduling, config, enum-validation |
| (missing ;base64 marker) | validation | error | base64, data-uri, image-input, validation |
| Image index out of range | validation | error | validation, index-out-of-range, image-decoding, sgldiffusion |
| k_mode must not be empty | validation | error | multimodal, video, config-validation, valueerror |
| strict fl2va packed layout requires keyframe_frame_indices | validation | error | missing-parameter, minimax-h3, packed-sequence |
| text must be str, got | validation | error | inkling, tokenizer, type-error, encode |
| Empty host in address | validation | error | network, address-parsing, hostname, sglang |
| batching config rule device_memory_gb_min must be <=… | validation | error | config, batching, validation, range-check, gpu-memory |
| Unknown token_type , only support "text" or "image". | validation | error | sglang, longcat-image, token-type, position-ids, invalid-argument |
| unsupported MiniMax H3 condition type | validation | error | minimax-h3, condition-type, enum-validation |
| forward() is not supported in encoder_only mode. Use… | exception | error | asr, encoder-only, api-misuse, multimodal |
| SANA-WM action and camera_to_world/camera_path are mutually… | validation | error | sglang, sana-wm, action-conditioning, mutually-exclusive-args, camera-control |
| unused video block token count entries | validation | error | minimax-h3, ref2va, alignment |
| video reference requires block token counts and timestamps | validation | error | minimax-h3, ref2va, video-presentation, alignment |
| cache_salt should be a list or a string. | validation | error | sglang, cache-salt, type-error |
| MiniMax H3 image material uses an unsupported format | validation | error | minimax-h3, image-format, unsupported-format |
| Every cache_salt should be a string. | validation | error | sglang, cache-salt, type-error, input-validation |
| QKV tensors must be CUDA bfloat16 tensors | validation | error | dtype, device, rope, bfloat16, hunyuan |
| seqused_k tensor must be Int32 | validation | error | cuda, dtype, flash-attention, masking, int32 |
| seqused_q tensor must be Int32 | validation | error | cuda, dtype, flash-attention, masking, int32 |
| kv-canary: has_swa_lut must be bool, got | validation | error | kv-canary, type-check, argument-validation |
| MiniMax H3 tasks require the video_vae output decoder | error_code | critical | minimax-h3, vae, missing-module, decoding |
| is required and must be an object | validation | error | minimax-h3, request-validation, target-object, canonical-request |
| composite_input input_types must contain non-empty strings | validation | error | realtime, event-validation, composite-input, type-mismatch |
| Either chunk_index or chunk_size must be provided. | validation | error | sana-wm, chunking, missing-argument |
| huggingface_hub is required to download Real-ESRGAN… | exception | error | realesrgan, huggingface, dependency, postprocess |
| invalid duration in action segment | validation | error | validation, action-string, duration, sana-wm |
| must be a non-negative finite number | validation | error | minimax-h3, request-validation, non-negative-float, nan-inf |
| tar material payload is truncated with | validation | error | tar, truncation, race-condition |
| batching config rule max_batch_size must be >= 1 | validation | error | config, batching, validation, range-check |
| chunk_index must be strictly increasing, got | validation | error | sana-wm, chunking, invalid-argument, ordering |
| encoder_hidden_states must be provided. | validation | error | stable-diffusion-3, missing-argument, text-embedding |
| Invalid VAE type | validation | error | mova-audio-dit, vae-type, unsupported-config |
| SANA-WM forward_long requires encoder_hidden_states. | validation | error | sana-wm, forward-long, missing-argument |
| Vision tp_size and tp_rank must be set together | validation | error | qwen3-vl, vision, tensor-parallel, argument-validation |
| kv_gather_degree does not compose with ulysses_degree or… | validation | error | parallelism, config, validation |
| Only 'rms_norm_across_heads' is supported as a valid value… | validation | error | qk-norm, unsupported-feature, ltx-2 |
| Value error, parameter top_n should be larger than 0. | validation | error | embeddings, validation, openai-api, sglang |
| Component attention backend key must not be empty | validation | error | config, validation, attention-backend |
| indices must be contiguous | validation | error | contiguity, indices, sparse-attention |
| material URI has invalid base64 padding | validation | error | minimax-h3, base64, padding, material-uri |
| MiniMax H3 audio material has no usable channel count | validation | error | minimax-h3, channels, ffprobe, audio |
| Unsupported SANA-WM update_rule | validation | error | sana-wm, gdn, invalid-enum, config |
| --bcg-text-buckets must contain at least one positive… | validation | error | cuda-graph, buckets, config-validation |
| indices must be a CUDA tensor | validation | error | device-validation, cuda, indices, sparse-mla |
| must be a positive finite number | validation | error | minimax-h3, request-validation, positive-float, nan-inf |
| pixel_values_videos and video_grid_thw must be given… | exception | error | minimax-h3, encode-ids, paired-args, video-input |
| tar material payload is truncated: expected | validation | error | tar, truncation, minimax-h3 |
| You must specify exactly one of input_ids or inputs_embeds | exception | error | mistral-3, forward, mutually-exclusive-args, input-validation |
| keyframe condition rows require plan.task='fl2va' or… | validation | error | minimax-h3, keyframe, task-mismatch |
| kv-canary: write_req_capacity must be non-negative, got | validation | error | kv-canary, capacity, argument-validation |
| must not mix nested and flat entries | validation | error | minimax-h3, shape-validation, video-presentation |
| NvidiaKDAKernel is prefill-only | exception | error | sglang, nvidia, kda, decode, not-implemented |
| strict fl2va packed layout requires integer… | validation | error | type-validation, numpy, minimax-h3 |
| topk_length must be contiguous | validation | error | contiguity, topk |
| encoded keyframe condition rows must be a mapping | validation | error | minimax-h3, keyframe, type-validation |
| must be a sequence | validation | error | minimax-h3, type-validation, video-presentation |
| SANA-WM stage-1 expects exactly one Gemma-2 text encoder. | validation | error | model-config, text-encoder, sana-wm |