-
Notifications
You must be signed in to change notification settings - Fork 652
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Tests] Add example tests to cover
compress_xxx.pyscripts in compressed-tensorscompressed-tensorsRelates to compressed-tensorsRelates to compressed-tensorsenhancementNew feature or requestNew feature or requestgood 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.Remove Excessive Offload Writes - Buffer Writes in disable_offloading Context
enhancementNew feature or requestNew feature or requestStatus: Open.#3136 In vllm-project/llm-compressor;Overlap Compression with Sequential Onload/Offload
enhancementNew feature or requestNew feature or requestStatus: Open.#3135 In vllm-project/llm-compressor;Overlap MoE Linearization with Sequential Onload/Offload
enhancementNew feature or requestNew feature or requestStatus: Open.#3134 In vllm-project/llm-compressor;Group Disk Reads by Safetensors File - Reduce File/Mapping Overhead
enhancementNew feature or requestNew feature or requestStatus: Open.#3133 In vllm-project/llm-compressor;Streaming Subgraph Prefetching - Overlap Disk I/O with Computation
enhancementNew feature or requestNew feature or requestStatus: Open.#3132 In vllm-project/llm-compressor;Streaming Model Saving - Integrate Checkpoint Writing into Pipeline
enhancementNew feature or requestNew feature or requestStatus: Open.#3131 In vllm-project/llm-compressor;- Status: Open.#3129 In vllm-project/llm-compressor;
[RFC] Weight Streaming and Offload Performance improvements
enhancementNew feature or requestNew feature or requestStatus: Open.- Status: Open.#3119 In vllm-project/llm-compressor;
- Status: Open.#3106 In vllm-project/llm-compressor;
- Status: Open.#3103 In vllm-project/llm-compressor;