Search results

[Feature]: Support vLLM with Python 3.14

feature requestNew feature or requestNew feature or request

Status: Open.

#34096 In vllm-project/vllm;

· mgoin opened on Feb 8, 2026

[Usage]: Option to set system_fingerprint?

usageHow to use vllmHow to use vllm

Status: Open.

#34095 In vllm-project/vllm;

· vrdn-23 opened on Feb 8, 2026

[Bug]: assert num_cache_lines >= batch

bugSomething isn't workingSomething isn't working

Status: Open.

#34094 In vllm-project/vllm;

· vitalik opened on Feb 8, 2026

what am I doing wrong ? libmpi_cxx.so.40: cannot open shared object file: No such file or directory

usageHow to use vllmHow to use vllm

Status: Open.

#34090 In vllm-project/vllm;

· peter247 opened on Feb 8, 2026

[Bug]: KV Cache Memory Bottleneck Calculation in Pipeline Parallel (_check_enough_kv_cache_memory in get_kv_cache_configs)

bugSomething isn't workingSomething isn't working

Status: Open.

#34076 In vllm-project/vllm;

· chizhiwei opened on Feb 8, 2026

[Bug]: #33758 is causing aiohttp/_websocket.c build error

bugSomething isn't workingSomething isn't working

rocmRelated to AMD ROCmRelated to AMD ROCm

Status: Open.

#34073 In vllm-project/vllm;

· amd-hhashemi opened on Feb 8, 2026

[Feature]: nightly docker and wheels for ROCm

feature requestNew feature or requestNew feature or request

rocmRelated to AMD ROCmRelated to AMD ROCm

Status: Open.

#34067 In vllm-project/vllm;

· hongxiayang opened on Feb 7, 2026

[Bug]: pd disaggregation on the same host with nixl connector can not use nvlink to transfer kv cache

bugSomething isn't workingSomething isn't working

Status: Open.

#34054 In vllm-project/vllm;

· ChowXu opened on Feb 7, 2026

[Bug]: required numpy version mismatch between modules

bugSomething isn't workingSomething isn't working

Status: Open.

#34041 In vllm-project/vllm;

· llsj14 opened on Feb 7, 2026

[Doc]: Setting Encoder Cache for MultiModal LLMs

documentationImprovements or additions to documentationImprovements or additions to documentation

Status: Open.

#34040 In vllm-project/vllm;

· willingWill17 opened on Feb 7, 2026

[Bug]: vLLM-compile should not execute the decoder forward pass during compilation

bugSomething isn't workingSomething isn't working

torch.compile

Status: Open.

#34034 In vllm-project/vllm;

· zou3519 opened on Feb 7, 2026

[Usage]: Unable to load Mistral-Small-3.2-24B-Instruct-2506-FP8 due to "Value error, Found unknown quantization", but the same configs worked for vllm v0.11.0

usageHow to use vllmHow to use vllm

Status: Open.

#34028 In vllm-project/vllm;

· gabinguo opened on Feb 6, 2026