qwen3.8-flash-next_p150x4 is an open-weight model from Sam Jett. Its published files total 1.9 GB.
Qwen3.8-Flash-Next (48 hybrid layers: gated delta-net, sparse attention with an indexer, a 512-expert top-10 MoE at BF4, plus a PLE n-gram layer) served through vLLM and the Tenstorrent vLLM plugin on 4x p150 (a QuietBox or four p150 cards) or on a QuietBox 2…
Parameters—
Context—
Weights1.9 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
Qwen3.8-Flash-Next (48 hybrid layers: gated delta-net, sparse attention with an indexer, a 512-expert top-10 MoE at BF4, plus a PLE n-gram layer) served through vLLM and the Tenstorrent vLLM plugin on 4x p150 (a QuietBox or four p150 cards) or on a QuietBox 2 (2x p300c). One interactive user at a time; contexts of 32k, 64k or 128k tokens; thinking off by default. Updated 2026-09-26: prefill in 2048-row slabs by default (1,990 prompt tokens/s), decode 29.1 tokens/s greedy / 27.4 sampled at batch 1 (fork commit ce5b0f8eb6eb). Runs on 4x p150 (a QuietBox or four p150 cards; profiles c32k, c64k, c128k, c32k-quietbox) and on a QuietBox 2 (2x p300c; the default c32k or c32k-quietbox2) — see the…
Excerpt from the card by Sam Jett.
Identity and Version
- Repository
- sjettTT/qwen3.8-flash-next_p150x4
- Publisher
- Sam Jett
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- ebddd379eda45706f7c3b1e625d8c65101fad727
- First published
- 2026-09-17
- Last updated
- 2026-09-26
Files and Weights
544 files, 1.9 GB in total.
Configuration390 files · 9.8 MB
Documentation34 files · 403.7 KB
Other119 files · 1.9 GB
Repository1 file · 4.8 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| code/models/common/auto_compose.py | Configuration | 5.9 KB | — |
| code/models/common/device_utils.py | Configuration | 1.5 KB | — |
| code/models/common/distribute_as.py | Configuration | 4.9 KB | — |
| code/models/common/generation_utils.py | Configuration | 11.4 KB | — |
| code/models/common/helper_funcs.py | Configuration | 1.2 KB | — |
| code/models/common/lightweightmodule.py | Configuration | 405 B | — |
| code/models/common/llama_models.py | Configuration | 7.0 KB | — |
| code/models/common/llm_runtime/config.py | Configuration | 5.8 KB | — |
| code/models/common/llm_runtime/decode.py | Configuration | 57.3 KB | — |
| code/models/common/llm_runtime/execution.py | Configuration | 33.0 KB | — |
| code/models/common/llm_runtime/lane_group.py | Configuration | 46.1 KB | — |
| code/models/common/llm_runtime/output_reader.py | Configuration | 8.7 KB | — |
| code/models/common/llm_runtime/paged_kv_cache.py | Configuration | 16.7 KB | — |
| code/models/common/llm_runtime/prefill/config.py | Configuration | 14.8 KB | — |
| code/models/common/llm_runtime/prefill/inputs.py | Configuration | 14.0 KB | — |
| code/models/common/llm_runtime/prefill/plan.py | Configuration | 20.6 KB | — |
| code/models/common/llm_runtime/prefill/postprocess.py | Configuration | 15.5 KB | — |
| code/models/common/llm_runtime/prefill/result_collector.py | Configuration | 7.8 KB | — |
| code/models/common/llm_runtime/prefill/runtime.py | Configuration | 20.8 KB | — |
| code/models/common/llm_runtime/prefill/sampling_helpers.py | Configuration | 2.8 KB | — |
| code/models/common/llm_runtime/prefill/sequence_runner.py | Configuration | 5.6 KB | — |
| code/models/common/llm_runtime/prefill/signatures.py | Configuration | 7.4 KB | — |
| code/models/common/llm_runtime/prefill/trace.py | Configuration | 12.2 KB | — |
| code/models/common/llm_runtime/program_compiler.py | Configuration | 12.2 KB | — |
| code/models/common/llm_runtime/tensor_resources.py | Configuration | 3.5 KB | — |
| code/models/common/llm_runtime/trace_compiler.py | Configuration | 19.8 KB | — |
| code/models/common/llm_runtime/vllm_adapter.py | Configuration | 17.1 KB | — |
| code/models/common/llm_runtime/warmup.py | Configuration | 33.0 KB | — |
| code/models/common/metrics.py | Configuration | 20.3 KB | — |
| code/models/common/model_capabilities.py | Configuration | 3.2 KB | — |
| code/models/common/models/deepseek_r1_distill_qwen_14b/__init__.py | Configuration | 1.3 KB | — |
| code/models/common/models/deepseek_r1_distill_qwen_14b/executor.py | Configuration | 27.1 KB | — |
| code/models/common/models/deepseek_r1_distill_qwen_14b/generator.py | Configuration | 18.0 KB | — |
| code/models/common/models/deepseek_r1_distill_qwen_14b/hf_adaptor.py | Configuration | 13.0 KB | — |
| code/models/common/models/deepseek_r1_distill_qwen_14b/model.py | Configuration | 46.8 KB | — |
| code/models/common/models/deepseek_r1_distill_qwen_14b/weight_utils.py | Configuration | 8.8 KB | — |
| code/models/common/models/executor.py | Configuration | 29.0 KB | — |
| code/models/common/models/llama32_1b/__init__.py | Configuration | 785 B | — |
| code/models/common/models/llama32_1b/executor.py | Configuration | 578 B | — |
| code/models/common/models/llama32_1b/generator.py | Configuration | 17.5 KB | — |
| code/models/common/models/llama32_1b/hf_adaptor.py | Configuration | 10.5 KB | — |
| code/models/common/models/llama32_1b/model.py | Configuration | 45.0 KB | — |
| code/models/common/models/llama32_1b/weight_utils.py | Configuration | 3.9 KB | — |
| code/models/common/models/llama32_3b/__init__.py | Configuration | 785 B | — |
| code/models/common/models/llama32_3b/executor.py | Configuration | 578 B | — |
| code/models/common/models/llama32_3b/generator.py | Configuration | 17.9 KB | — |
| code/models/common/models/llama32_3b/hf_adaptor.py | Configuration | 10.6 KB | — |
| code/models/common/models/llama32_3b/model.py | Configuration | 44.6 KB | — |
| code/models/common/models/llama32_3b/weight_utils.py | Configuration | 7.0 KB | — |
| code/models/common/models/llama33_70b/__init__.py | Configuration | 1.6 KB | — |
| code/models/common/models/llama33_70b/executor.py | Configuration | 589 B | — |
| code/models/common/models/llama33_70b/generator.py | Configuration | 18.9 KB | — |
| code/models/common/models/llama33_70b/hf_adaptor.py | Configuration | 12.8 KB | — |
| code/models/common/models/llama33_70b/model.py | Configuration | 52.8 KB | — |
| code/models/common/models/llama33_70b/weight_utils.py | Configuration | 7.0 KB | — |
| code/models/common/models/llama3_8b/executor.py | Configuration | 545 B | — |
| code/models/common/models/llama3_8b/generator.py | Configuration | 17.6 KB | — |
| code/models/common/models/llama3_8b/hf_adaptor.py | Configuration | 20.8 KB | — |
| code/models/common/models/llama3_8b/model.py | Configuration | 77.7 KB | — |
| code/models/common/models/llama3_executor.py | Configuration | 18.7 KB | — |
| code/models/common/models/mistral_7b/__init__.py | Configuration | 1.2 KB | — |
| code/models/common/models/mistral_7b/executor.py | Configuration | 26.9 KB | — |
| code/models/common/models/mistral_7b/generator.py | Configuration | 17.7 KB | — |
| code/models/common/models/mistral_7b/hf_adaptor.py | Configuration | 12.8 KB | — |
| code/models/common/models/mistral_7b/model.py | Configuration | 38.4 KB | — |
| code/models/common/models/mistral_7b/weight_utils.py | Configuration | 7.1 KB | — |
| code/models/common/models/phi4/__init__.py | Configuration | 1.1 KB | — |
| code/models/common/models/phi4/executor.py | Configuration | 26.8 KB | — |
| code/models/common/models/phi4/generator.py | Configuration | 17.6 KB | — |
| code/models/common/models/phi4/hf_adaptor.py | Configuration | 12.6 KB | — |
| code/models/common/models/phi4/model.py | Configuration | 38.0 KB | — |
| code/models/common/models/phi4/weight_utils.py | Configuration | 9.2 KB | — |
| code/models/common/models/qwen25_72b/__init__.py | Configuration | 1.2 KB | — |
| code/models/common/models/qwen25_72b/executor.py | Configuration | 1.2 KB | — |
| code/models/common/models/qwen25_72b/generator.py | Configuration | 13.8 KB | — |
| code/models/common/models/qwen25_72b/hf_adaptor.py | Configuration | 13.4 KB | — |
| code/models/common/models/qwen25_72b/model.py | Configuration | 50.9 KB | — |
| code/models/common/models/qwen25_72b/weight_utils.py | Configuration | 9.0 KB | — |
| code/models/common/models/qwen25_72b/weights.py | Configuration | 383 B | — |
| code/models/common/models/qwen25_7b/__init__.py | Configuration | 923 B | — |
| code/models/common/models/qwen25_7b/executor.py | Configuration | 655 B | — |
| code/models/common/models/qwen25_7b/generator.py | Configuration | 17.6 KB | — |
| code/models/common/models/qwen25_7b/hf_adaptor.py | Configuration | 11.1 KB | — |
| code/models/common/models/qwen25_7b/model.py | Configuration | 47.4 KB | — |
| code/models/common/models/qwen25_7b/weight_utils.py | Configuration | 8.6 KB | — |
| code/models/common/models/qwen25_coder_32b/__init__.py | Configuration | 1.6 KB | — |
| code/models/common/models/qwen25_coder_32b/demo.py | Configuration | 23.8 KB | — |
| code/models/common/models/qwen25_coder_32b/executor.py | Configuration | 3.6 KB | — |
| code/models/common/models/qwen25_coder_32b/generator.py | Configuration | 13.9 KB | — |
| code/models/common/models/qwen25_coder_32b/hf_adaptor.py | Configuration | 13.5 KB | — |
| code/models/common/models/qwen25_coder_32b/model.py | Configuration | 57.4 KB | — |
| code/models/common/models/qwen25_coder_32b/weight_utils.py | Configuration | 8.8 KB | — |
| code/models/common/models/qwen2_7b/__init__.py | Configuration | 895 B | — |
| code/models/common/models/qwen2_7b/executor.py | Configuration | 640 B | — |
| code/models/common/models/qwen2_7b/generator.py | Configuration | 17.6 KB | — |
| code/models/common/models/qwen2_7b/hf_adaptor.py | Configuration | 11.1 KB | — |
| code/models/common/models/qwen2_7b/model.py | Configuration | 48.4 KB | — |
| code/models/common/models/qwen2_7b/weight_utils.py | Configuration | 8.6 KB | — |
| code/models/common/models/qwen2_executor.py | Configuration | 18.1 KB | — |
| code/models/common/models/qwen3_32b/__init__.py | Configuration | 896 B | — |
| code/models/common/models/qwen3_32b/demo.py | Configuration | 23.7 KB | — |
| code/models/common/models/qwen3_32b/executor.py | Configuration | 13.4 KB | — |
| code/models/common/models/qwen3_32b/generator.py | Configuration | 13.9 KB | — |
| code/models/common/models/qwen3_32b/hf_adaptor.py | Configuration | 11.3 KB | — |
| code/models/common/models/qwen3_32b/model.py | Configuration | 58.1 KB | — |
| code/models/common/models/qwen3_32b/weight_utils.py | Configuration | 12.1 KB | — |
| code/models/common/modules/attention/attention_1d.py | Configuration | 119.5 KB | — |
| code/models/common/modules/embedding/embedding_1d.py | Configuration | 9.7 KB | — |
| code/models/common/modules/lazy_buffer.py | Configuration | 7.0 KB | — |
| code/models/common/modules/lazy_weight.py | Configuration | 13.5 KB | — |
| code/models/common/modules/lm_head/lm_head_1d.py | Configuration | 24.1 KB | — |
| code/models/common/modules/mlp/mlp_1d.py | Configuration | 49.3 KB | — |
| code/models/common/modules/mlp/mlp_2d.py | Configuration | 33.3 KB | — |
| code/models/common/modules/moe/configs/deepseek_ocr.yaml | Configuration | 934 B | — |
| code/models/common/modules/moe/configs/deepseek_v3.yaml | Configuration | 740 B | — |
| code/models/common/modules/moe/configs/deepseek_v3_single_glx.yaml | Configuration | 739 B | — |
| code/models/common/modules/moe/configs/deepseek_v4_flash.yaml | Configuration | 1.1 KB | — |
| code/models/common/modules/moe/configs/deepseek_v4_pro.yaml | Configuration | 1.1 KB | — |
| code/models/common/modules/moe/configs/gemma_4_26b.yaml | Configuration | 1.7 KB | — |
| code/models/common/modules/moe/configs/glm5.yaml | Configuration | 935 B | — |
| code/models/common/modules/moe/configs/glm_47.yaml | Configuration | 1.1 KB | — |
| code/models/common/modules/moe/configs/gpt_oss.yaml | Configuration | 1.2 KB | — |
| code/models/common/modules/moe/configs/kimi_k25.yaml | Configuration | 968 B | — |
| code/models/common/modules/moe/configs/ling_1t.yaml | Configuration | 834 B | — |
| code/models/common/modules/moe/configs/mistral_large_3.yaml | Configuration | 846 B | — |
| code/models/common/modules/moe/configs/qwen35_35b.yaml | Configuration | 814 B | — |
| code/models/common/modules/moe/configs/qwen35_397b.yaml | Configuration | 1.1 KB | — |
| code/models/common/modules/moe/configs/qwen3_235b.yaml | Configuration | 970 B | — |
| code/models/common/modules/moe/configs/qwen3_omni_talker.yaml | Configuration | 1.1 KB | — |
| code/models/common/modules/moe/configs/qwen3_omni_thinker.yaml | Configuration | 986 B | — |
| code/models/common/modules/moe/tt_moe_decode.py | Configuration | 47.0 KB | — |
| code/models/common/modules/moe/tt_moe_decode_config.py | Configuration | 35.4 KB | — |
| code/models/common/modules/moe/tt_moe_decode_config_schemas.py | Configuration | 4.1 KB | — |
| code/models/common/modules/moe/tt_moe_gate.py | Configuration | 49.3 KB | — |
| code/models/common/modules/moe/tt_moe_gate_config.py | Configuration | 5.2 KB | — |
| code/models/common/modules/rmsnorm/rmsnorm_1d.py | Configuration | 32.3 KB | — |
| code/models/common/modules/rmsnorm/rmsnorm_2d.py | Configuration | 18.7 KB | — |
| code/models/common/modules/rope/rope_1d.py | Configuration | 19.4 KB | — |
| code/models/common/modules/sampling/params.py | Configuration | 23.4 KB | — |
| code/models/common/modules/sampling/penalties_1d.py | Configuration | 29.4 KB | — |
| code/models/common/modules/sampling/sampling_1d.py | Configuration | 36.2 KB | — |
| code/models/common/modules/sampling/sampling_state_1d.py | Configuration | 39.7 KB | — |
| code/models/common/modules/sampling/seed_manager_1d.py | Configuration | 27.7 KB | — |
| code/models/common/modules/tt_ccl.py | Configuration | 7.0 KB | — |
| code/models/common/reference_rope.py | Configuration | 3.2 KB | — |
| code/models/common/rmsnorm.py | Configuration | 10.7 KB | — |
| code/models/common/sampling/__init__.py | Configuration | 1.9 KB | — |
| code/models/common/sampling/_utils.py | Configuration | 1.3 KB | — |
| code/models/common/sampling/generator.py | Configuration | 56.3 KB | — |
| code/models/common/sampling/sampling_params.py | Configuration | 731 B | — |
| code/models/common/sampling/tt_log_probs.py | Configuration | 34.8 KB | — |
| code/models/common/sampling/tt_penalties.py | Configuration | 18.5 KB | — |
| code/models/common/sampling/tt_sampling.py | Configuration | 59.7 KB | — |
| code/models/common/sampling/vocab_padding.py | Configuration | 5.6 KB | — |
| code/models/common/tensor_utils.py | Configuration | 8.1 KB | — |
| code/models/common/tests/conftest.py | Configuration | 16.6 KB | — |
| code/models/common/tests/demos/cleanup_utils.py | Configuration | 3.1 KB | — |
| code/models/common/tests/demos/deepseek_r1_distill_qwen_14b/__init__.py | Configuration | 94 B | — |
| code/models/common/tests/demos/deepseek_r1_distill_qwen_14b/demo.py | Configuration | 63.2 KB | — |
| code/models/common/tests/demos/deepseek_r1_distill_qwen_14b/generate_book_refpt.py | Configuration | 6.0 KB | — |
| code/models/common/tests/demos/llama32_1b/__init__.py | Configuration | 91 B | — |
| code/models/common/tests/demos/llama32_1b/demo.py | Configuration | 52.8 KB | — |
| code/models/common/tests/demos/llama32_3b/__init__.py | Configuration | 91 B | — |
| code/models/common/tests/demos/llama32_3b/demo.py | Configuration | 53.2 KB | — |
| code/models/common/tests/demos/llama33_70b/__init__.py | Configuration | 91 B | — |
| code/models/common/tests/demos/llama33_70b/demo.py | Configuration | 55.3 KB | — |
| code/models/common/tests/demos/llama3_8b/demo.py | Configuration | 52.0 KB | — |
| code/models/common/tests/demos/llama3_8b/demo_utils.py | Configuration | 8.0 KB | — |
| code/models/common/tests/demos/llama3_8b/sample_prompts/input_data_questions_prefill_128.json | Configuration | 12.6 KB | — |
| code/models/common/tests/demos/mistral_7b/demo.py | Configuration | 54.8 KB | — |
| code/models/common/tests/demos/phi4/__init__.py | Configuration | 94 B | — |
| code/models/common/tests/demos/phi4/demo.py | Configuration | 58.9 KB | — |
| code/models/common/tests/demos/qwen25_72b/demo.py | Configuration | 58.2 KB | — |
| code/models/common/tests/demos/qwen25_72b/generate_controlled_refpt.py | Configuration | 6.9 KB | — |
| code/models/common/tests/demos/qwen25_7b/demo.py | Configuration | 65.1 KB | — |
| code/models/common/tests/demos/qwen25_coder_32b/demo.py | Configuration | 58.5 KB | — |
| code/models/common/tests/demos/qwen2_7b/__init__.py | Configuration | 91 B | — |
| code/models/common/tests/demos/qwen2_7b/demo.py | Configuration | 64.2 KB | — |
| code/models/common/tests/demos/qwen2_7b/generate_controlled_refpt.py | Configuration | 5.4 KB | — |
| code/models/common/tests/demos/qwen3_32b/demo.py | Configuration | 96.3 KB | — |
| code/models/common/tests/demos/run_helpers.py | Configuration | 44.7 KB | — |
| code/models/common/tests/demos/test_cleanup_utils.py | Configuration | 5.6 KB | — |
| code/models/common/tests/demos/test_run_helpers.py | Configuration | 24.4 KB | — |
| code/models/common/tests/host/test_metrics_pytorch_only.py | Configuration | 2.5 KB | — |
| code/models/common/tests/host/test_utility_functions_imports.py | Configuration | 1.3 KB | — |
| code/models/common/tests/llm_runtime/test_config.py | Configuration | 4.6 KB | — |
| code/models/common/tests/llm_runtime/test_decode_runtime.py | Configuration | 47.8 KB | — |
| code/models/common/tests/llm_runtime/test_execution.py | Configuration | 32.3 KB | — |
| code/models/common/tests/llm_runtime/test_executor_integration.py | Configuration | 73.8 KB | — |
| code/models/common/tests/llm_runtime/test_lane_group.py | Configuration | 48.0 KB | — |
| code/models/common/tests/llm_runtime/test_llama3_8b_integration.py | Configuration | 38.7 KB | — |
| code/models/common/tests/llm_runtime/test_llama3_8b_model_contract.py | Configuration | 12.6 KB | — |
| code/models/common/tests/llm_runtime/test_model_contract.py | Configuration | 36.1 KB | — |
| code/models/common/tests/llm_runtime/test_model_executor.py | Configuration | 11.4 KB | — |
| code/models/common/tests/llm_runtime/test_output_reader.py | Configuration | 7.1 KB | — |
| code/models/common/tests/llm_runtime/test_paged_kv_cache.py | Configuration | 14.3 KB | — |
| code/models/common/tests/llm_runtime/test_prefill_inputs.py | Configuration | 5.9 KB | — |
| code/models/common/tests/llm_runtime/test_prefill_runtime.py | Configuration | 109.1 KB | — |
| code/models/common/tests/llm_runtime/test_program_compiler.py | Configuration | 9.2 KB | — |
| code/models/common/tests/llm_runtime/test_tensor_resources.py | Configuration | 2.3 KB | — |
| code/models/common/tests/llm_runtime/test_trace_compiler.py | Configuration | 21.7 KB | — |
| code/models/common/tests/llm_runtime/test_vllm_adapter.py | Configuration | 38.0 KB | — |
| code/models/common/tests/llm_runtime/test_warmup.py | Configuration | 36.4 KB | — |
| code/models/common/tests/models/deepseek_r1_distill_qwen_14b/test_demo_contract.py | Configuration | 17.6 KB | — |
| code/models/common/tests/models/deepseek_r1_distill_qwen_14b/test_hf_adaptor.py | Configuration | 11.2 KB | — |
| code/models/common/tests/models/deepseek_r1_distill_qwen_14b/test_prefill_last_token_contract.py | Configuration | 2.5 KB | — |
| code/models/common/tests/models/llama32_1b/test_batched_prefill_postprocess.py | Configuration | 3.3 KB | — |
| code/models/common/tests/models/llama32_1b/test_demo_warmup.py | Configuration | 5.2 KB | — |
| code/models/common/tests/models/llama32_1b/test_hf_adaptor.py | Configuration | 10.0 KB | — |
| code/models/common/tests/models/llama32_3b/test_batched_prefill_postprocess.py | Configuration | 3.3 KB | — |
| code/models/common/tests/models/llama32_3b/test_demo_warmup.py | Configuration | 8.3 KB | — |
| code/models/common/tests/models/llama32_3b/test_hf_adaptor.py | Configuration | 12.2 KB | — |
| code/models/common/tests/models/llama33_70b/logits_oracle.py | Configuration | 5.9 KB | — |
| code/models/common/tests/models/llama33_70b/test_demo_contract.py | Configuration | 19.9 KB | — |
| code/models/common/tests/models/llama33_70b/test_hf_adaptor.py | Configuration | 12.8 KB | — |
| code/models/common/tests/models/llama33_70b/test_logits_oracle.py | Configuration | 3.2 KB | — |
| code/models/common/tests/models/llama33_70b/test_model_profile.py | Configuration | 11.1 KB | — |
| code/models/common/tests/models/llama33_70b/test_p150x4_smoke.py | Configuration | 6.5 KB | — |
| code/models/common/tests/models/llama33_70b/test_t3k_batched_prefill_correctness.py | Configuration | 28.5 KB | — |
| code/models/common/tests/models/llama3_8b/test_demo_contract.py | Configuration | 9.2 KB | — |
| code/models/common/tests/models/llama3_8b/test_model_profile.py | Configuration | 11.6 KB | — |
| code/models/common/tests/models/mistral_7b/test_demo_contract.py | Configuration | 10.0 KB | — |
| code/models/common/tests/models/mistral_7b/test_hf_adaptor.py | Configuration | 6.4 KB | — |
| code/models/common/tests/models/mistral_7b/test_prefill_last_token_contract.py | Configuration | 2.3 KB | — |
| code/models/common/tests/models/phi4/test_demo_contract.py | Configuration | 14.9 KB | — |
| code/models/common/tests/models/phi4/test_hf_adaptor.py | Configuration | 7.5 KB | — |
| code/models/common/tests/models/qwen25_72b/test_demo_contract.py | Configuration | 5.5 KB | — |
| code/models/common/tests/models/qwen25_72b/test_hf_adaptor.py | Configuration | 6.9 KB | — |
| code/models/common/tests/models/qwen25_72b/test_model_runtime_surface.py | Configuration | 5.2 KB | — |
| code/models/common/tests/models/qwen25_7b/test_demo_contract.py | Configuration | 16.4 KB | — |
| code/models/common/tests/models/qwen25_7b/test_hf_adaptor.py | Configuration | 10.2 KB | — |
| code/models/common/tests/models/qwen25_coder_32b/test_demo_contract.py | Configuration | 4.4 KB | — |
| code/models/common/tests/models/qwen25_coder_32b/test_hf_adaptor.py | Configuration | 7.0 KB | — |
| code/models/common/tests/models/qwen25_coder_32b/test_model_runtime_surface.py | Configuration | 5.2 KB | — |
| code/models/common/tests/models/qwen2_7b/test_demo_contract.py | Configuration | 16.4 KB | — |
| code/models/common/tests/models/qwen2_7b/test_hf_adaptor.py | Configuration | 10.1 KB | — |
| code/models/common/tests/models/qwen3_32b/test_demo_contract.py | Configuration | 28.0 KB | — |
| code/models/common/tests/models/qwen3_32b/test_hf_adaptor.py | Configuration | 6.7 KB | — |
| code/models/common/tests/models/qwen3_32b/test_model_runtime_surface.py | Configuration | 9.6 KB | — |
| code/models/common/tests/models/qwen3_32b/test_module_profiles.py | Configuration | 11.9 KB | — |
| code/models/common/tests/models/qwen3_32b/test_p150x4_smoke.py | Configuration | 6.2 KB | — |
| code/models/common/tests/models/test_qwen2_executor_family.py | Configuration | 4.4 KB | — |
| code/models/common/tests/modules/attention/profiling/test_attention_1d_profiling.py | Configuration | 35.1 KB | — |
| code/models/common/tests/modules/attention/test_attention_1d.py | Configuration | 133.7 KB | — |
| code/models/common/tests/modules/attention/test_attention_1d_arch_config.py | Configuration | 9.9 KB | — |
| code/models/common/tests/modules/embedding/test_embedding_1d.py | Configuration | 26.5 KB | — |
| code/models/common/tests/modules/lm_head/test_lm_head_1d.py | Configuration | 28.0 KB | — |
| code/models/common/tests/modules/mlp/test_mlp_1d.py | Configuration | 71.5 KB | — |
| code/models/common/tests/modules/mlp/test_mlp_1d_arch_config.py | Configuration | 7.1 KB | — |
| code/models/common/tests/modules/mlp/test_mlp_2d.py | Configuration | 18.3 KB | — |
| code/models/common/tests/modules/moe/test_generalized_moe_gate.py | Configuration | 26.9 KB | — |
| code/models/common/tests/modules/moe/test_tt_moe_decode.py | Configuration | 26.6 KB | — |
| code/models/common/tests/modules/moe/test_tt_moe_gate.py | Configuration | 11.4 KB | — |
| code/models/common/tests/modules/rmsnorm/test_rmsnorm_1d.py | Configuration | 69.9 KB | — |
| code/models/common/tests/modules/rmsnorm/test_rmsnorm_2d.py | Configuration | 11.6 KB | — |
| code/models/common/tests/modules/rope/test_rope_1d.py | Configuration | 43.6 KB | — |
| code/models/common/tests/modules/sampling/test_params.py | Configuration | 12.1 KB | — |
| code/models/common/tests/modules/sampling/test_penalties_1d.py | Configuration | 78.2 KB | — |
| code/models/common/tests/modules/sampling/test_sampling_1d.py | Configuration | 71.4 KB | — |
| code/models/common/tests/modules/sampling/test_sampling_1d_release.py | Configuration | 8.5 KB | — |
| code/models/common/tests/modules/sampling/test_sampling_state_1d.py | Configuration | 31.2 KB | — |
| code/models/common/tests/modules/sampling/test_seed_manager_1d.py | Configuration | 12.5 KB | — |
| code/models/common/tests/modules/test_lazy_buffer.py | Configuration | 8.3 KB | — |
| code/models/common/tests/modules/test_tensor_utils.py | Configuration | 11.7 KB | — |
| code/models/common/tests/test_auto_compose.py | Configuration | 16.5 KB | — |
| code/models/common/tests/test_bh_required_capabilities.py | Configuration | 28.1 KB | — |
| code/models/common/tests/test_device_lock.py | Configuration | 4.0 KB | — |
| code/models/common/tests/test_distribute_as.py | Configuration | 8.6 KB | — |
| code/models/common/tests/test_lazy_weight.py | Configuration | 38.5 KB | — |
| code/models/common/tests/test_llama3_8b_hf_adaptor.py | Configuration | 5.3 KB | — |
| code/models/common/tests/test_mesh_fixture_policy.py | Configuration | 2.7 KB | — |
| code/models/common/tests/test_metrics.py | Configuration | 27.4 KB | — |
| code/models/common/tests/test_resume_offset_alignment.py | Configuration | 7.7 KB | — |
| code/models/common/tests/test_sampling.py | Configuration | 72.4 KB | — |
| code/models/common/tests/test_sampling_vocab_padding.py | Configuration | 3.7 KB | — |
| code/models/common/tests/test_tt_log_probs_state.py | Configuration | 2.3 KB | — |
| code/models/common/tests/test_tt_sampling.py | Configuration | 96.1 KB | — |
| code/models/common/tests/test_utils.py | Configuration | 1.7 KB | — |
| code/models/common/tests/test_validation_tools.py | Configuration | 24.6 KB | — |
| code/models/common/tests/utils.py | Configuration | 682 B | — |
| code/models/common/utility_functions.py | Configuration | 46.6 KB | — |
| code/models/common/utils.py | Configuration | 4.6 KB | — |
| code/models/common/validation_tools.py | Configuration | 29.1 KB | — |
| code/models/common/warmup/__init__.py | Configuration | 175 B | — |
| code/models/common/warmup/warmup_utils.py | Configuration | 5.3 KB | — |
| code/models/common/weight_cache.py | Configuration | 20.7 KB | — |
| code/models/demos/blackhole/qwen36/__init__.py | Configuration | — | |
| code/models/demos/blackhole/qwen36/tt/__init__.py | Configuration | — | |
| code/models/demos/blackhole/qwen36/tt/attention/__init__.py | Configuration | 536 B | — |
| code/models/demos/blackhole/qwen36/tt/attention/config.py | Configuration | 568 B | — |
| code/models/demos/blackhole/qwen36/tt/attention/decode.py | Configuration | 1.5 KB | — |
| code/models/demos/blackhole/qwen36/tt/attention/gated_attention.py | Configuration | 4.6 KB | — |
| code/models/demos/blackhole/qwen36/tt/attention/prefill.py | Configuration | 3.1 KB | — |
| code/models/demos/blackhole/qwen36/tt/attention/rope_tp.py | Configuration | 16.8 KB | — |
| code/models/demos/blackhole/qwen36/tt/attention/tp.py | Configuration | 39.7 KB | — |
| code/models/demos/blackhole/qwen36/tt/attention/weights.py | Configuration | 1.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/chat.py | Configuration | 24.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/checkpoint.py | Configuration | 18.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/config.py | Configuration | 11.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/diagnostic_bf4.py | Configuration | 24.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/reference.py | Configuration | 20.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-chat-greedy.json | Configuration | 78.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-code-greedy.json | Configuration | 76.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-fact-greedy.json | Configuration | 55.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-json-greedy.json | Configuration | 76.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-list-greedy.json | Configuration | 77.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-math-greedy.json | Configuration | 77.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-multilingual-greedy.json | Configuration | 67.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-prose-greedy.json | Configuration | 78.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-refactor-greedy.json | Configuration | 79.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-sky-greedy.json | Configuration | 24.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-story-greedy.json | Configuration | 77.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/prompt-summary-greedy.json | Configuration | 73.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/evidence_records.py | Configuration | 2.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/hardware_profiles.py | Configuration | 14.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/live_decode_diagnostic.py | Configuration | 58.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/physical_route.py | Configuration | 11.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/prewarm_ple_table.py | Configuration | 6.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qwen38_chat_protocol.py | Configuration | 19.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qwen38_chat_session.py | Configuration | 135.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qwen38_prefill_driver.py | Configuration | 21.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qwen38_sampling_step.py | Configuration | 57.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qwen38_vllm.py | Configuration | 37.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/resident_decode.py | Configuration | 12.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/runtime_admission.py | Configuration | 10.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/vllm_bundle/qwen38/vllm_metadata.json | Configuration | 145 B | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/__init__.py | Configuration | 180 B | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/gdn.py | Configuration | 12.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/gr.py | Configuration | 11.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/layer.py | Configuration | 6.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/model.py | Configuration | 16.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/moe.py | Configuration | 16.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/ple.py | Configuration | 11.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tt/qsa.py | Configuration | 16.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/__init__.py | Configuration | 6.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/bf4.py | Configuration | 96.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/builder.py | Configuration | 66.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/contracts.py | Configuration | 35.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/decode.py | Configuration | 36.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/decode_matmul.py | Configuration | 22.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/device_sampler.py | Configuration | 32.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/diagnostic_decode.py | Configuration | 5.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/embedding.py | Configuration | 118.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/final_mixer.py | Configuration | 28.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fixed_five.py | Configuration | 37.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/__init__.py | Configuration | 1.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/final_mixer/__init__.py | Configuration | 23.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gdn_step/__init__.py | Configuration | 13.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_fold/__init__.py | Configuration | 37.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/__init__.py | Configuration | 39.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_write/__init__.py | Configuration | 9.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/greedy_tail/__init__.py | Configuration | 29.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/moe_post/__init__.py | Configuration | 14.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/__init__.py | Configuration | 37.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/position_derive/__init__.py | Configuration | 22.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/program.py | Configuration | 13.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/__init__.py | Configuration | 60.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/registry.py | Configuration | 8.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/router_tail/__init__.py | Configuration | 17.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/sampler_tail/__init__.py | Configuration | 15.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/shared_expert/__init__.py | Configuration | 12.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/untilize_rows/__init__.py | Configuration | 3.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/gdn.py | Configuration | 181.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/gr.py | Configuration | 57.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/hybrid_decode.py | Configuration | 98.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/lanes.py | Configuration | 46.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/layer.py | Configuration | 87.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/model.py | Configuration | 166.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/moe.py | Configuration | 104.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/mtp.py | Configuration | 32.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/mtp_decode.py | Configuration | 46.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/mtp_draft.py | Configuration | 74.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/mtp_lanes.py | Configuration | 128.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/mtp_mechanics.py | Configuration | 4.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/mtp_v2.py | Configuration | 144.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/ple.py | Configuration | 97.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/prefill_dense.py | Configuration | 35.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/prefill_glue.py | Configuration | 6.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/qsa.py | Configuration | 394.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/sampling.py | Configuration | 58.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/speculative_sampling.py | Configuration | 4.0 KB | — |
| code/models/experimental/gated_attention_gated_deltanet/tt/__init__.py | Configuration | — | |
| code/models/experimental/gated_attention_gated_deltanet/tt/ttnn_delta_rule_ops.py | Configuration | 19.0 KB | — |
| code/models/experimental/gated_attention_gated_deltanet/tt/ttnn_delta_rule_seq.py | Configuration | 31.7 KB | — |
| code/models/experimental/gated_attention_gated_deltanet/tt/ttnn_gated_attention.py | Configuration | 26.2 KB | — |
| code/models/experimental/gated_attention_gated_deltanet/tt/ttnn_gated_deltanet.py | Configuration | 28.3 KB | — |
| code/models/tt_transformers/tt/ccl.py | Configuration | 17.6 KB | — |
| image/index.json | Configuration | 384 B | — |
| image/manifest.json | Configuration | 1.9 KB | — |
| tt_kernel_manifest.json | Configuration | 8.0 KB | — |
| README.md | Documentation | 7.8 KB | — |
| code/models/common/LICENSE-Llama-3.1 | Documentation | 7.7 KB | — |
| code/models/common/README.md | Documentation | 11.7 KB | — |
| code/models/common/llm_runtime/README.md | Documentation | 24.1 KB | — |
| code/models/common/llm_runtime/prefill/README.md | Documentation | 13.2 KB | — |
| code/models/common/llm_runtime/tttv2_demo_to_vllm_integration_skill.md | Documentation | 23.9 KB | — |
| code/models/common/models/deepseek_r1_distill_qwen_14b/README.md | Documentation | 3.2 KB | — |
| code/models/common/models/llama32_1b/README.md | Documentation | 2.0 KB | — |
| code/models/common/models/llama32_3b/README.md | Documentation | 1.9 KB | — |
| code/models/common/models/llama33_70b/README.md | Documentation | 2.2 KB | — |
| code/models/common/models/llama3_8b/README.md | Documentation | 17.6 KB | — |
| code/models/common/models/mistral_7b/README.md | Documentation | 2.7 KB | — |
| code/models/common/models/phi4/README.md | Documentation | 2.7 KB | — |
| code/models/common/models/qwen25_72b/README.md | Documentation | 1.9 KB | — |
| code/models/common/models/qwen25_7b/README.md | Documentation | 1.7 KB | — |
| code/models/common/models/qwen25_coder_32b/README.md | Documentation | 1.9 KB | — |
| code/models/common/models/qwen2_7b/README.md | Documentation | 1.8 KB | — |
| code/models/common/models/qwen3_32b/README.md | Documentation | 3.8 KB | — |
| code/models/common/modules/README.md | Documentation | 11.9 KB | — |
| code/models/common/modules/moe/configs/models_table.md | Documentation | 3.3 KB | — |
| code/models/common/sampling/README.md | Documentation | 5.8 KB | — |
| code/models/common/tests/modules/attention/low_pcc_notes.md | Documentation | 6.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/README.md | Documentation | 26.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/NUMERICS.md | Documentation | 21.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/PREFILL.md | Documentation | 23.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/PROOFS.md | Documentation | 9.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/SERVER.md | Documentation | 28.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/TESTING.md | Documentation | 6.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/dev/mtp-lanes/STAGE-0-20260920.md | Documentation | 16.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/dev/mtp-lanes/STAGE-1-20260920.md | Documentation | 16.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/dev/mtp-lanes/STAGE-2-20260920.md | Documentation | 22.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/dev/mtp-lanes/STAGE-3-20260920.md | Documentation | 25.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/dev/mtp-lanes/STAGE-4-20260920.md | Documentation | 9.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/docs/dev/upstream-moe/UPSTREAM-MOE-PRS-20260925.md | Documentation | 38.7 KB | — |
| code/models/common/tests/requirements.txt | Other | 11 B | — |
| code/models/common/tests/setup.cfg | Other | 224 B | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/cpu-oracle-two-step.jsonl | Other | 26.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/acceptance/greedy-prompts/SHA256SUMS | Other | 1.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qb2_p300_1x4_line_mesh_graph_descriptor.textproto | Other | 646 B | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qb_p150_x4_1x4_line_mesh_graph_descriptor.textproto | Other | 548 B | — |
| code/models/demos/blackhole/qwen38_flash_next/tools/qb_p150_x4_1x4_ring_mesh_graph_descriptor.textproto | Other | 503 B | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/final_mixer/kernels/lowrank_reduce_compute.cpp | Other | 4.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/final_mixer/kernels/lowrank_reduce_reader.cpp | Other | 3.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/final_mixer/kernels/lowrank_reduce_writer.cpp | Other | 1.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gdn_step/kernels/compute.cpp | Other | 20.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gdn_step/kernels/reader.cpp | Other | 9.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gdn_step/kernels/writer.cpp | Other | 3.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_fold/kernels/mcast_writer2.cpp | Other | 2.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_fold/kernels/sem_probe.cpp | Other | 1.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_fold/kernels/stats_norm_compute.cpp | Other | 6.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_fold/kernels/transport.cpp | Other | 2.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_fold/kernels/transport2.cpp | Other | 4.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_fold/kernels/transport_phase.h | Other | 11.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/down_compute.cpp | Other | 3.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/gate_compute.cpp | Other | 5.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/lowrank_compute.cpp | Other | 3.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/mcast_phase.h | Other | 4.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/mcast_reader.cpp | Other | 3.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/mcast_writer.cpp | Other | 2.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/noc_probe.cpp | Other | 1.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/norm_compute.cpp | Other | 4.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/reader.cpp | Other | 5.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/stats_compute.cpp | Other | 2.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_read/kernels/writer.cpp | Other | 2.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_write/kernels/compute.cpp | Other | 2.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_write/kernels/reader.cpp | Other | 3.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/gr_write/kernels/writer.cpp | Other | 1.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/greedy_tail/kernels/merge.cpp | Other | 11.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/greedy_tail/kernels/resolve.cpp | Other | 5.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/greedy_tail/kernels/scan.cpp | Other | 12.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/moe_post/kernels/compute_moe_post.cpp | Other | 5.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/moe_post/kernels/reader_moe_post.cpp | Other | 10.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/moe_post/kernels/writer_moe_post.cpp | Other | 1.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/kernels/conv_compute.cpp | Other | 8.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/kernels/conv_reader.cpp | Other | 6.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/kernels/conv_writer.cpp | Other | 3.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/kernels/gate_compute.cpp | Other | 7.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/kernels/gate_reader.cpp | Other | 4.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/kernels/gate_writer.cpp | Other | 2.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/ple/kernels/norm_gamma_rows_compute.cpp | Other | 4.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/position_derive/kernels/advance.cpp | Other | 1.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/position_derive/kernels/derive.cpp | Other | 13.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/position_derive/kernels/derive_lanes.cpp | Other | 12.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/index_tail_cbs.h | Other | 1.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/index_tail_compute_norm.cpp | Other | 2.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/index_tail_compute_rope.cpp | Other | 1.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/index_tail_reader_norm.cpp | Other | 5.6 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/index_tail_reader_rope.cpp | Other | 4.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/index_tail_writer_norm.cpp | Other | 5.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/index_tail_writer_rope.cpp | Other | 3.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/lane_score_rows.cpp | Other | 1.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_cbs.h | Other | 1.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_compute_norm.cpp | Other | 493 B | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_compute_rope.cpp | Other | 526 B | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_compute_staging.cpp | Other | 2.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_reader_norm.cpp | Other | 2.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_reader_rope.cpp | Other | 1.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_reader_staging.cpp | Other | 3.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_writer_norm.cpp | Other | 3.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_writer_rope.cpp | Other | 2.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/main_tail_writer_staging.cpp | Other | 3.0 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/positions.h | Other | 1.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/post_attention_compute.cpp | Other | 2.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/post_attention_reader.cpp | Other | 2.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/rms_norm_compute.cpp | Other | 687 B | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/rms_norm_mirror.h | Other | 5.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/rope_compute.cpp | Other | 3.3 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/rope_mirror.h | Other | 3.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/score_merge_compute.cpp | Other | 2.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/score_merge_reader.cpp | Other | 2.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/score_merge_writer.cpp | Other | 1.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/selection_row.cpp | Other | 4.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/tile_rows.h | Other | 2.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/qsa_block/kernels/widen_compute.cpp | Other | 1.1 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/router_tail/kernels/compute_router_tail.cpp | Other | 14.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/router_tail/kernels/reader_router_tail.cpp | Other | 5.8 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/router_tail/kernels/topk_lanes.h | Other | 13.5 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/router_tail/kernels/writer_router_tail.cpp | Other | 3.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/sampler_tail/kernels/sample.cpp | Other | 12.4 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/shared_expert/kernels/compute_shared_eltwise.cpp | Other | 4.2 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/shared_expert/kernels/reader_shared_eltwise.cpp | Other | 1.9 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/shared_expert/kernels/writer_shared_eltwise.cpp | Other | 1.7 KB | — |
| code/models/demos/blackhole/qwen38_flash_next/ttnn/fused/untilize_rows/kernels/writer_rows.cpp | Other | 2.2 KB | — |
| image/blobs/sha256/030c446970c22925ce4b337a93e486d41341a417ec699992a836b97a4fe38421 | Other | 6.6 KB | — |
| image/blobs/sha256/20c3783cc497b5b0df1fc5f92bd64c3d2fbb24057c88692c8fda205b6ea8a2f2 | Other | 29.8 MB | 20c3783cc497 |
| image/blobs/sha256/25fa9742fecd5438306f1095210d13d755e6669bc137a696524ca103b9c8a3e6 | Other | 69.5 MB | 25fa9742fecd |
| image/blobs/sha256/34cc26a2be36be343f4efba7e7f929ab7d04acea3561345736a6e5b8cc4a3756 | Other | 139.1 MB | 34cc26a2be36 |
| image/blobs/sha256/39ce132bdf0e120688d0e5b2d27f98a7834c720b5075a239d3e3febf53930c33 | Other | 2.3 MB | 39ce132bdf0e |
| image/blobs/sha256/3bfcbebe1d385f87493e20039df179f52e2ce02653ad82efc80d8c665a1fa76c | Other | 1.2 MB | 3bfcbebe1d38 |
| image/blobs/sha256/44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a | Other | 2 B | — |
| image/blobs/sha256/4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 | Other | 32 B | — |
| image/blobs/sha256/5a8d215907089f4ca8004c70f79d500f4a7cc98bb3d81c36755fc3fa7196a0b7 | Other | 4.4 KB | — |
| image/blobs/sha256/69f040a27bba9d6e0e6de3817bfa766ba962196df14e75e2fb070cd43c9841a0 | Other | 1.4 MB | 69f040a27bba |
| image/blobs/sha256/70562718e62c066c08fa707a0d404f2b1a857d309357c09bab39d7289d9c96a1 | Other | 856 B | — |
| image/blobs/sha256/773afa696947c6349e3730748346ca6d520288378022b7f4a6fd763158efda84 | Other | 14.9 KB | — |
| image/blobs/sha256/803d1a09a63cf6e8a4ce6ba6a3e793873d1293bd867b376422534b04daab6065 | Other | 116 B | — |
| image/blobs/sha256/89f2a9b17b066fdbadde9f338f727d50c7261cca2acda4111e367aaf54459f06 | Other | 11.4 MB | 89f2a9b17b06 |
| image/blobs/sha256/8cc643b329781be0bd7348577a200e1dab28425c0fa1fa2344548b4f9495dbe3 | Other | 1.9 KB | — |
| image/blobs/sha256/9103ce35628fca4558dbcb094371964a5ec80fb3832343bff6d53b7e26e0ef92 | Other | 837 B | — |
| image/blobs/sha256/9286679d19123e7e0d9ab3355eec49a45555a9f4b6958a8d64cb337b4fefbbfb | Other | 57.8 MB | 9286679d1912 |
| image/blobs/sha256/9e704fe3cb6099e39ee710f2c9a998dc41c0dbf1212d7799711513691ad460d8 | Other | 1.5 KB | — |
| image/blobs/sha256/b5cb943116cfe36961f30a54da6cda1807af9006eeb6574d0b7d3b566540cbae | Other | 1.1 KB | — |
| image/blobs/sha256/bcc2682a74f7f60dd349cd2e71c0c6e66041c3ace75ffd05850da3c2320f626d | Other | 38.0 MB | bcc2682a74f7 |
| image/blobs/sha256/de18f4418a276d988165dba086043e96851c3f0d086da624f42bd764a9080918 | Other | 3.9 KB | — |
| image/blobs/sha256/e0a3e6cb6a3b515456369fe79c6e4cdb2a89f00847da88cad68cc3c5f3af9af7 | Other | 1.2 KB | — |
| image/blobs/sha256/e23bd31d5538c0429199e2f7b9ff1eec7f04be903ab15977c509d64c6f4f830a | Other | 9.6 MB | e23bd31d5538 |
| image/blobs/sha256/e5e02e774f57b4ffc7a1336c97cdcc0a96d37aac71a884cf9001e6d181ad7048 | Other | 4.5 KB | — |
| image/blobs/sha256/e8b78f95366027e3935c11f4d558713154303b07ad251716ee7aa13dd562b490 | Other | 38.0 MB | e8b78f953660 |
| image/blobs/sha256/e8d51d031ca038dca81e34507d425f78c06205149041e556897dcc2381412d63 | Other | 1.4 GB | e8d51d031ca0 |
| image/blobs/sha256/fa700a75beec4884428d888c6abd2f55713f8321db13a2d566176cddd100bd97 | Other | 31.2 MB | fa700a75beec |
| image/blobs/sha256/fbaab1fb25724ff90452121e864094344e34b445cb3d563c14deca37524784b9 | Other | 138.9 MB | fbaab1fb2572 |
| image/oci-layout | Other | 30 B | — |
| requirements.lock | Other | 4.5 KB | — |
| .gitattributes | Repository | 4.8 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
Download from Sam Jett
Released by Sam Jett through its official repository on Hugging Face.