-
Notifications
You must be signed in to change notification settings - Fork 169
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Feature]: support and eval H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference
enhancementNew feature or requestNew feature or requestStatus: Open.[Bug]: imbalanced memory usages across cards
bugSomething isn't workingSomething isn't workingStatus: Open.[Bug]: regression mxfp4 fake accuracy is much higher
bugSomething isn't workingSomething isn't workingStatus: Open.[Feature]: support reap
enhancementNew feature or requestNew feature or requestStatus: Open.- Status: Open.
[Bug]: deepseek v3.2 torch compile exception
bugSomething isn't workingSomething isn't workingStatus: Open.[Feature]: support FP8+WOQ mix datatypes inference in transformers and vllm
enhancementNew feature or requestNew feature or requestStatus: Open.[Bug]: unexpected enable_quant_input: false in config.json for FP8_BLOCK
bugSomething isn't workingSomething isn't workingStatus: Open.[Feature]: svdquant supports llm and other schemes(W2A16)
enhancementNew feature or requestNew feature or requestStatus: Open.[Bug]: qwen3.8-27B q2ks is larger than unsloth's Q2KL
enhancementNew feature or requestNew feature or requestStatus: Open.[Bug]: ARK SageV1 BF16 D128 causes DEVICE_LOST on Windows Arc B580
bugSomething isn't workingSomething isn't workingStatus: Open.#2213 In intel/auto-round;- Status: Open.