-
Notifications
You must be signed in to change notification settings - Fork 195
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
neuronx-cc 2.26.6360.0: NCC_IBIR227 'Axis not found in current loop nest' on a fixed-shape autoregressive decode loop, reproducible and deterministic, sensitive to Python call-site depth
bugSomething isn't workingSomething isn't workingStatus: Open.#1386 In aws-neuron/aws-neuron-sdk;Silent miscompilation of masked assignment, plus 3 defects and a bf16 regression, on a dilated CNN (trn2, neuronxcc-2.26.6360.0)
bugSomething isn't workingSomething isn't workingStatus: Open.#1381 In aws-neuron/aws-neuron-sdk;[neuron compiler backend] reg_dce incorrectly removes dependencies
bugSomething isn't workingSomething isn't workingStatus: Open.#1380 In aws-neuron/aws-neuron-sdk;Extremely long compile times and high compiler memory usage for some large NKI kernels
bugSomething isn't workingSomething isn't workingStatus: Open.#1374 In aws-neuron/aws-neuron-sdk;[NCC_ICFG001] shard_on_i_hybrid MoE kernel fails to compile at seq_len > 2048 (multiple exit nodes in sg0000)
bugSomething isn't workingSomething isn't workingStatus: Open.#1372 In aws-neuron/aws-neuron-sdk;[vllm-neuron 0.21.0.1.0.0] neuronx-cc compilation failed with 70 at tp_barrier — intermittent cold-compile crash at TP=64 (trn2.48xlarge)
bugSomething isn't workingSomething isn't workingStatus: Open.#1369 In aws-neuron/aws-neuron-sdk;[vllm-neuron 0.21.0.1.0.0] Compiled NEFF cache not reused across pods — VLLM_NEURON_REMOTE_CACHE has no effect (full recompile every cold start)
bugSomething isn't workingSomething isn't workingStatus: Open.#1368 In aws-neuron/aws-neuron-sdk;neuronx-cc INTERNAL_ERROR NCC_IBIR297 (bir::samePartitionsAll in ModuleForkPass) compiling an MLA + 256-expert MoE decode graph on trn2
bugSomething isn't workingSomething isn't workingStatus: Open.#1362 In aws-neuron/aws-neuron-sdk;One-time NeuronCore runtime init (~6.7s in nrt_init/tdrv_init) dominates process startup — can it be shared/reduced?
bugSomething isn't workingSomething isn't workingStatus: Open.#1361 In aws-neuron/aws-neuron-sdk;Support StableHLO/PJRT graph-level memory placement and data movement betwen memories
documentationImprovements or additions to documentationImprovements or additions to documentationStatus: Open.#1340 In aws-neuron/aws-neuron-sdk;Neuron PJRT StableHLO compile rewrites sort+slice sampling path to AwsNeuronTopK with full vocab size as k
bugSomething isn't workingSomething isn't workingStatus: Open.#1339 In aws-neuron/aws-neuron-sdk;Inf2 ERROR NRT:nrt_allocate_neuron_cores
bugSomething isn't workingSomething isn't workingStatus: Open.#1338 In aws-neuron/aws-neuron-sdk;