Search results

[Bug]: Gemma 4 E2B QAT checkpoints fail to load: k_norm required for KV-shared layers (num_kv_shared_layers ignored by loader)

Status: Open.

#3225 In vllm-project/tpu-inference;

· xbill9 opened on Jul 21, 2026

[Feature] Make Vit Encoder CUDA graph feature work with Qwen3-VL moe

Status: Open.

#3164 In vllm-project/tpu-inference;

· lk-chen opened on Jul 13, 2026

[Performance]: unconditional fp32 logits convert + aliasing copy costs ~12% of the greedy decode step (Gemma 2B, v5e, batch 512)

Status: Open.

#3127 In vllm-project/tpu-inference;

· RubensZimbres opened on Jul 9, 2026

[Bug]: kv_cache_dtype=fp8 silently allocates bf16 on v5e (RPA v3) while logging that fp8 is active

bugSomething isn't workingSomething isn't working

Status: Open.

#3126 In vllm-project/tpu-inference;

· RubensZimbres opened on Jul 9, 2026

[Bug]: BATCHED_RPA_KERNEL does not work with speculative decoding

bugSomething isn't workingSomething isn't working

Status: Open.

#3095 In vllm-project/tpu-inference;

· amanseervi opened on Jul 7, 2026

DeepSeek-V4 dp-attention: per-request seq_len capped at ~num_gpu_blocks/attn_dp_size due to compressor state cache block_size=1

Status: Open.

#3081 In vllm-project/tpu-inference;

· zorrofox opened on Jul 6, 2026

general_device_put OOMs under native jax.distributed multi-host when target sharding is replicated across processes

Status: Open.

#3077 In vllm-project/tpu-inference;

· zorrofox opened on Jul 5, 2026

TPUOffloadConnector: reproducible TPU CoreHalt (E0200) in D2H save path at 8192-token prefill (stable at 2048)

Status: Open.

#3076 In vllm-project/tpu-inference;

· lokic233 opened on Jul 5, 2026

Question about process_awq_moe_weights

Status: Open.

#3049 In vllm-project/tpu-inference;

· yuanfz98 opened on Jun 30, 2026

[Bug]: EP behavior difference in flax_nnx vs. torchax path

bugSomething isn't workingSomething isn't working

Status: Open.

#3041 In vllm-project/tpu-inference;

· lk-chen opened on Jun 29, 2026

[Bug]: AssertionError in set_forward_context during Qwen3-30B-A3B-Thinking AOT Pre-compilation with DP > 1

bugSomething isn't workingSomething isn't working

Status: Open.

#3026 In vllm-project/tpu-inference;

· gangchen03 opened on Jun 26, 2026

[Feature]: Support native JAX GPT-OSS MXFP4 quantization loading

Status: Open.

#2952 In vllm-project/tpu-inference;

· Leo7Deng opened on Jun 21, 2026