model: MTP support for Qwen3-Next by yomaytk · Pull Request #25589 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/25589

Story Details

Last Updated
Total Articles	1

Main Topics

Llama (language model)

#llama-language-model

large language model by Meta AI

Handle

#handle

part of a device designed to be held

Similar to This

github.com Oct 17

model : add Kolibri-1 (Aleph-Alpha) support by riteme · Pull Request #30673 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30673

0 similar articles

github.com Oct 15

model: add Muse Spark Open (text, vision and audio) by ServeurpersoCom · Pull Request #30616 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30616

0 similar articles

github.com Oct 10

[Model] Support MiniCPM-V 4.7 by tc-mb · Pull Request #29416 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/29416

0 similar articles

github.com Sep 16

Enable CUDA graph for MTP draft by gaugarg-nv · Pull Request #28549 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/28549

0 similar articles

github.com Aug 20

AVX2: Speed up large batch size prompt processing of IQ models by bartowski1182 · Pull Request #27402 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/27402

0 similar articles

github.com Aug 17

spec : add adaptive MTP draft depth (draft-mtp-adaptive) by stew675 · Pull Request #27210 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/27210

0 similar articles

github.com Aug 03

model : support MTP in GLM-4.5-Air by jacekpoplawski · Pull Request #26534 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/26534

0 similar articles

github.com Aug 02

DeepseekV4 MTP + DSpark by am17an · Pull Request #25784 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an ...

github.com/ggml-org/llama.cpp/pull/25784

0 similar articles

126

github.com Jul 27

mtp nextn offload by John-194 · Pull Request #26177 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an ...

github.com/ggml-org/llama.cpp/pull/26177

0 similar articles

github.com Jul 14

model: add Hy3 (hy_v3) support with MTP speculative decoding by satindergrewal · Pull Request #25395 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/25395

0 similar articles

github.com Jul 02

[SYCL] Flash Attention with XMX engine via oneDNN graph API (SDPA) on KV f16; Qwen3.6-27b-Q8_0 prefill speed up x1.21 at p=512 and x4 ...

github.com/ggml-org/llama.cpp/pull/25222

0 similar articles

github.com Jun 10

Remove padding and multiple D2D copies for MTP by gaugarg-nv · Pull Request #24086 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/24086

0 similar articles

github.com Jun 09

ggml-webgpu: Improve prefill speeds for k-quants + refactor matmul for Q4/Q5/Q8 and k-quants by yomaytk · Pull Request #24225 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/24225

0 similar articles

github.com Jun 08

mtp: support for gemma-4 E2B and E4B assistants by max-krasnyansky · Pull Request #24282 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/24282

0 similar articles

github.com Jun 05

Qwen3.6 + MTP: Calculated context size is smaller when I use `--spec-draft-type-* q4_0`. is this normal? · ggml-org/llama.cpp · Discussion #24102

github.com/ggml-org/llama.cpp/discussions/24102

0 similar articles

github.com May 20

llama : add Gemma4 MTP by am17an · Pull Request #23398 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an ...

github.com/ggml-org/llama.cpp/pull/23398

0 similar articles

173

github.com May 19

llama : MTP clean-up by ggerganov · Pull Request #23269 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an ...

github.com/ggml-org/llama.cpp/pull/23269

0 similar articles

github.com May 17

llama: avoid copying logits during prompt decode in MTP by am17an · Pull Request #23198 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/23198

0 similar articles

github.com Feb 08

[Model] Qwen3.5 dense and MoE support (no vision) by pwilkin · Pull Request #19435 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/19435

0 similar articles