Open Issues Need Help
View All on GitHub remove cpu-roundtrip for `reshape_and_cache` 2 days ago
help wanted vllm-spyre-next vllm-spyre-attention-backend August2026
[FP8] Support block-wise FP8 quantization 3 days ago
enhancement help wanted vllm-spyre-next August2026
[FP8] Support FP8 KV cache for attention 3 days ago
enhancement help wanted vllm-spyre-next August2026
enhancement help wanted vllm-spyre-next August2026
enhancement help wanted vllm-spyre-next tests August2026
[FP8] Add FP8 support to ParallelLMHead 3 days ago
enhancement help wanted vllm-spyre-next August2026
enhancement help wanted vllm-spyre-next August2026
enhancement help wanted vllm-spyre-next August2026
enhancement help wanted vllm-spyre-next August2026
enhancement help wanted vllm-spyre-next August2026
enhancement help wanted vllm-spyre-next August2026
help wanted vllm-spyre-next vllm-spyre-attention-backend August2026
help wanted vllm-spyre-next vllm-spyre-attention-backend
Evaluate whether vLLM IR can be used to wrap layers for torch-spyre about 2 months ago
good first issue vllm-spyre-next July2026
[Feature]: Configure individual layers on spyre about 2 months ago
enhancement good first issue vllm-spyre-next
[Epic] Ensure that the new plugin is robust to upstream changes about 2 months ago
help wanted vllm-spyre-next
[Epic] Develop KVCacheConnector for Spyre about 2 months ago
help wanted vllm-spyre-next
[Epic] Support prefill/decode disaggregation about 2 months ago
help wanted vllm-spyre-next
Verify the 4D matmul in the attention computation 3 months ago
good first issue vllm-spyre-next June2026
Write design docs for key features 3 months ago
good first issue May2026
Wrap the ParallelLMHead for torch-spyre 3 months ago
good first issue vllm-spyre-next
[doc] add a README.md 4 months ago
documentation good first issue