Search results

[Bug] DFlash 2 speculative decoding crashes and fails in Python due to missing ctx_other and non-autoregressive graph execution

Status: Open.

#2361 In abetlen/llama-cpp-python;

· ilperev opened on Aug 20, 2026

uv add llama-cpp-python wheels fails for versions above 0.3.30

Status: Open.

#2352 In abetlen/llama-cpp-python;

· Karthik777 opened on Jul 31, 2026

Support sm100 and sm120 in CUDA pre‑built wheels

Status: Open.

#2341 In abetlen/llama-cpp-python;

· XuehaoSun opened on Jul 16, 2026

Request for Gemma 3 4B & Gemma 4 Integration Support with llama-cpp-python

Status: Open.

#2231 In abetlen/llama-cpp-python;

· LeConsulat2 opened on May 25, 2026

Gemma 4 tool calls returned as raw native tokens in content instead of tool_calls

Status: Open.

#2227 In abetlen/llama-cpp-python;

· ThiruvarankanM opened on May 22, 2026

Llava15ChatHandler - Cache Image Encoding

Status: Open.

#2222 In abetlen/llama-cpp-python;

· d-orm opened on May 17, 2026

Asset seeder disabled 'resemble-perth' not found. watermarking will be unavailable.

Status: Open.

#2219 In abetlen/llama-cpp-python;

· andymoorey opened on May 16, 2026

Llama.embed() calls LlamaBatch.add_sequence with old 3-arg signature; missing logits_array

Status: Open.

#2211 In abetlen/llama-cpp-python;

· emptyngton opened on May 9, 2026

Llama() silently accepts and discards embedding kwarg; .embed() then raises confusingly

Status: Open.

#2210 In abetlen/llama-cpp-python;

· emptyngton opened on May 9, 2026

Can RotorQuant/TurboQuant and dflash support be added?

Status: Open.

#2184 In abetlen/llama-cpp-python;

· Sourajit1234 opened on Apr 16, 2026

How to use "Gemma-4-E4B-it-heretic-GGUF" ?

Status: Open.

#2175 In abetlen/llama-cpp-python;

· TimmyHeart opened on Apr 6, 2026

Improve error messages

Status: Open.

#2145 In abetlen/llama-cpp-python;

· mausch opened on Mar 22, 2026