-
-
Notifications
You must be signed in to change notification settings - Fork 19.5k
All issues
Issue creation is restricted in this repository
- #42770 · WoosukKwon opened
on May 15, 2026 20 - #44280 · BugenZhao opened
on Jun 2, 2026 16 - #48168 · simon-mo opened
on Jul 9, 2026 1
Issues
is:issue state:open
is:issue state:open
Search results
[Bug]: Failed to initialize FlashInfer All Reduce workspace: CUDA driver error: invalid device ordinal
bugSomething isn't workingSomething isn't workingStatus: Open.#48823 In vllm-project/vllm;- Status: Open.#48819 In vllm-project/vllm;
[Bug]: The Deepseek v4 model compiles kenrel during the inference process
bugSomething isn't workingSomething isn't workingStatus: Open.#48809 In vllm-project/vllm;[Bug]: DP request distribution becomes imbalanced under long-context workload on H20 GPU
bugSomething isn't workingSomething isn't workingStatus: Open.#48808 In vllm-project/vllm;[Bug]: "There are significant spike issues in TTFT" with Kimi-K2.6-NVFP4
bugSomething isn't workingSomething isn't workingStatus: Open.#48803 In vllm-project/vllm;[Bug]: vLLM+LMCache GLM-5.2 inference causes engine RPCTimeout
bugSomething isn't workingSomething isn't workingStatus: Open.#48801 In vllm-project/vllm;[Bug]: Qwen3.5-35B FP8 kv cache is slower than BF16 kv cache on SM90 (Hopper)
bugSomething isn't workingSomething isn't workingStatus: Open.#48786 In vllm-project/vllm;- Status: Open.#48766 In vllm-project/vllm;
[Bug]: disable_any_whitespace is silently ignored at the request level (xgrammar)
bugSomething isn't workingSomething isn't workingStatus: Open.#48765 In vllm-project/vllm;- Status: Open.#48753 In vllm-project/vllm;
- Status: Open.#48752 In vllm-project/vllm;
[Bug]: [MRV2] MTP speculative decoding crashes with cudaErrorStreamCaptureUnsupported during CUDA graph capture
bugSomething isn't workingSomething isn't workingStatus: Open.#48749 In vllm-project/vllm;