-
-
Notifications
You must be signed in to change notification settings - Fork 339
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
- Status: Open.#817 In turboderp-org/exllamav2;
[BUG] System freeze during inference with RTX 5060 Ti via Thunderbolt 5 eGPU on Linux (kernel freeze, SSH drop, GPU fan full speed)
bugSomething isn't workingSomething isn't workingStatus: Open.#813 In turboderp-org/exllamav2;- Status: Open.#811 In turboderp-org/exllamav2;
- Status: Open.#810 In turboderp-org/exllamav2;
[QUESTION] Inquiry about DynamicGenerator: EOS not returned until max_new_tokens reached, despite stop_conditions
bugSomething isn't workingSomething isn't workingStatus: Open.#809 In turboderp-org/exllamav2;[BUG] 2080ti outputs gibberish
bugSomething isn't workingSomething isn't workingStatus: Open.#808 In turboderp-org/exllamav2;[QUESTION] I cannot achieve token/s speed as in your tests even with better GPU
bugSomething isn't workingSomething isn't workingStatus: Open.#806 In turboderp-org/exllamav2;- Status: Open.#804 In turboderp-org/exllamav2;
[BUG] [Cause Identified & Workarounds Proposed] Infinite Generation for Llama3 & Other Models with Multiple EOS IDs
bugSomething isn't workingSomething isn't workingStatus: Open.#803 In turboderp-org/exllamav2;[BUG] Unable to run examples/chat.py
bugSomething isn't workingSomething isn't workingStatus: Open.#802 In turboderp-org/exllamav2;- Status: Open.#798 In turboderp-org/exllamav2;
[BUG] ExLlamaV2Generator import broken across WHL & source repo — Windows 11 + RTX 5090 + CUDA 12.8 build inconsistencies
bugSomething isn't workingSomething isn't workingStatus: Open.#797 In turboderp-org/exllamav2;