diff --git a/.gitattributes b/.gitattributes index 4f078a9ce7a2211f3bee4b36d0576111bfb41a6c..07c18c84576628a0a5cdf6ec6b0764f07def9ba1 100644 --- a/.gitattributes +++ b/.gitattributes @@ -8159,3 +8159,20 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/wrapped_neff neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6ed6aa77ee480d24287c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6ed6aa77ee480d24287c.json new file mode 100644 index 0000000000000000000000000000000000000000..355c8460ae8515ab986c6b4072dd0cef6653e1d4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6ed6aa77ee480d24287c.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": true, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..757ef22adba051caf9112fe25b606c7fcd78c660 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:432507cb832f7729bbf0ea778b0674fbbcec5e2c99bc215a74bc9e18388ea0a7 +size 2769192 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..717d3321f4a14f87d505429b25af21ec08eaf70e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c2bffc8a4d4c372373af82a0d606c45371e8d5f1606a47deb19229175be9d7 +size 7640064 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..91fe16eaec348823e46292ff48083e41533aea5b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c89c12ac8e9d535f3e104d18529542875465ab04680b5116882999a4c89bf11 +size 2769048 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3f67f058b0ca7dee120f84ee8c026b52895d8fa2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba9699778492c5b80fabdfa844e21d1846b42cd01a45ff916e2c49cb2ec77b2 +size 8018944 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca2002d7158d98e12f2af7b78a00b19520665cf4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682fde39dd388b97be0388a0e7315e59904436ee6101f94251ca59c3f0b86771 +size 1844527 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..33e92257986f6b44113bbe12ec73b702c4a5a919 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a95f4126d9851f3be3907d9d36d66446b211ae2fa7e6ee53aac3b9b57c79370 +size 1373184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b714bdeb8961958b18d0c1c46acb493454b3396a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c16c1c48ed703f1ae029825c08170e5b116dce4033600da543b4b9e4565444 +size 1495658 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ad82c3e4810a40f2fe346ca3e9ca4673fff1fcd5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf76725cf4aed49731fe847e5391ca9ff0d1be5fdd188bcf48bac441996eaf90 +size 1877438 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..949de51387c9752aed0f7ad94467e146d249dfa6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0729939462c1c2f0279240784319f1a4e8d13e44ce8619308480ab79ff50b4 +size 1373184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..79e27e64a4a10687deb4373894c34e491454e82c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436ea39af68d5adf6e82e04b3d3c5a639dca7d985b782980458911445dae713e +size 1495658 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d614f688e68797bb9c0b098c344ca081c3c30f15 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b93bc610ed6e2b2c6523d6ec8d37f4e66d3b6f277809f66b86e857783284ff5 +size 2800179 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b8c1539171ba07b04a597d016423ec9698fad641 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b742c94d05ba5ecf96c93ceb10b822e42e3be072007bbc5de0fe74ce0b8c8afd +size 7967744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d5eaa28cc777468bdc237528a51bd3eb1a9591eb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b39b1035acb1d002e921f86caf315bb4ea10a30980cb4bcaf39ae5dd35706d +size 2766283 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..28042adf1ced6752c3f911a5ca1c73b4a7be40f7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476ce0289f7530fb642f878a204b661e1bea11fe8fb77dfc2d09d2a08aded105 +size 7967744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b2e06eb7526456ddce055020332cdaa305fc93ef --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab99eaef4f8cfe67b8635506cae450003067f2d7358b0685d9075c56b200df60 +size 2804218 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6bb8c23fb998abaaa00070362b0308ce265c9abb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a0e88589747a3d70246ba78b251b727f56b60e830df7fc927addd5e8cb5b00 +size 7650304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..79f5c94894f18a12cf3620658159a4ef25768402 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d05458ab59fc6f2531999e17b25b84162b3edc4ed6a749d613fe97e90d9f413 +size 2769120 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c45f3640b94ac8a3186e6e153d74aa2c2bc42dd0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc992616eafca636560202912d0d0e2246b5ff16d54e285b6c31f2cd774ab2c +size 7834624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a8c72fe9f6b121cab8763422030346dbbdd1cbd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2340b70dfa47166d1df502e73cb5b1acdc307eafde959caa31f2f91cf94498b1 +size 1844527 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d5a4e4b96b2d03ea8cb039944e4e4b2f627da5c4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdbe5da4f8dc160c4752e0c39699931aa864ce9e8ae2a41086a81281b416fe2 +size 1373184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5fe9b06375c73ee82538c8d3653f2796ab0b10cd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f246b3e78ad83fb93fbd374dadb1472cb102c966baabf7a52b4376a76d013d46 +size 1495658 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..236b480fb7c0a79a03982b100a6bbea67b2f12a9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9429fda17fc08d5991b6747d3a9866e6057084601ec96f814422ce5d4f5f815a +size 1885339 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..77fb56eb481c409c010f4a76a6bacd532426d8ba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7305ecb7a68336d5bf97c158223363289e613caa66e19683db7ba3ae598a5a75 +size 1342464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f331514b67f62883c7b6a6b208d9f5d6509d03b0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0e92e99c312a2d599e033dd9f271ad7d700556f5a0446b9db54aeb9ed31cc1 +size 1464853 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a7cbcbf5ae271f796fe03339aa5056956dc0a611 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89614bb24b5de480574220c100597fd203a9ccdfd1929fa4d97841f398da718 +size 1841801 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4cc6953c0bade76dd74d76b3f46b936afc74366f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ea6bcf0b6fcd0e285a976a0356c6a0fb3f8ff7f96ad3e66290032ce7912c54 +size 1342464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0c95da3888670fb8914c59a55917222a60bff47d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999a10be3d2890310776ff3e23d14ce727e1cda66c8e0fc1382f31161ab7c9b2 +size 1464853 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..26ea14f9f76a992f8b09d52b6486804fed0fc888 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe068dfaa913a97916fcc2488c5c77f80b191650b15912139178c1b0707b736 +size 1648464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a65fdca8029e1dbc86a98c4b3a03185697b2d333 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6939ca81ce4fce547b9afaa9f2f660351b9ab390610b49a80e0e3d2bfa476905 +size 8336384