-
Notifications
You must be signed in to change notification settings - Fork 619
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Bug] Fix ignore list for linear_attn with Qwen3.8
bugSomething isn't workingSomething isn't workinggood first issueA good first issue for users wanting to contributeA good first issue for users wanting to contributegood follow-up issueA good issue for users with some familiarity of the codebaseA good issue for users with some familiarity of the codebaseStatus: Open.- Status: Open.#3037 In vllm-project/llm-compressor;
[Feature] Multimodal calibration dataset support in oneshot
enhancementNew feature or requestNew feature or requestStatus: Open.#3032 In vllm-project/llm-compressor;- Status: Open.#3023 In vllm-project/llm-compressor;
- Status: Open.#3011 In vllm-project/llm-compressor;
FP4 Baseline Benchmarking - MoE (No Rotations)
documentationImprovements or additions to documentationImprovements or additions to documentationnvfp4For any PR / issue related to NVFP4 supportFor any PR / issue related to NVFP4 supportStatus: Open.[Bug]: Loading models with DDP leads to race condition on HF
cached_filesbugSomething isn't workingSomething isn't workinggood first issueA good first issue for users wanting to contributeA good first issue for users wanting to contributeStatus: Open.#2984 In vllm-project/llm-compressor;[Performance] Speed up subgraph tracing for large models
enhancementNew feature or requestNew feature or requestgood first issueA good first issue for users wanting to contributeA good first issue for users wanting to contributetracingIssues related to model tracingIssues related to model tracingStatus: Open.#2981 In vllm-project/llm-compressor;[Kimi-K3] Integrate KimiSparseMoeBlock with LinearExperts2D for REAP Support
enhancementNew feature or requestNew feature or requestgood first issueA good first issue for users wanting to contributeA good first issue for users wanting to contributeStatus: Open.#2979 In vllm-project/llm-compressor;[ModelFreePTQ] Memory issues with multi-gpu
enhancementNew feature or requestNew feature or requestgood first issueA good first issue for users wanting to contributeA good first issue for users wanting to contributemodel_free_ptqFor any PR/issue related to the `model_free_ptq` pathwayFor any PR/issue related to the `model_free_ptq` pathwayStatus: Open.#2975 In vllm-project/llm-compressor;- Status: Open.
- Status: Open.#2952 In vllm-project/llm-compressor;