gfx1201
Here are 46 public repositories matching this topic...
Measured llama.cpp benchmarks on AMD Radeon RDNA4 with ROCm: RX 9070 XT + Radeon AI PRO R9700 (48 GB). Qwen3.8, Gemma 4, GLM, gpt-oss; GGUF quant quality (KLD), MTP speculative decoding, 128K context, Claude Code with local models.
-
Updated
Nov 22, 2026 - Python
Drop-in SageAttention for AMD RX 9070 / 9070 XT (RDNA4, gfx1201): custom HIP attention kernels for fp16 and bf16, 1.06-2.2x faster than PR #368's gfx12 port over the full call. Prebuilt Windows wheels; ComfyUI uses it through --use-sage-attention.
-
Updated
Nov 7, 2026 - Python
Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
-
Updated
Oct 5, 2026 - Python
llama.cpp with native AMD RDNA4 (gfx1201) ROCm 7.11 support - 98.97 tok/s AI inference, competitive with RTX 4070 Ti, 32GB VRAM
-
Updated
Jan 3, 2026 - C++
Hardware-focused llama.cpp fork for Windows and dual AMD RDNA4 RX 9070 XT GPUs: ROCm/HIP + Vulkan backends, PyQt6 GUI (RDNA LLM Studio), MTP speculative decoding, FP8 attention, long-context Qwen3.8 benchmarks
-
Updated
Sep 26, 2026 - C++
Fine-tune your own LLM on an AMD Radeon GPU — the easy, tested way. QLoRA via ROCm on Windows/WSL2 & Linux, a worked Gemma-4 example, a reusable live training dashboard, and a smoke test that proves the loss falls.
-
Updated
Jun 20, 2026 - HTML
Qwen3.6-27B-FP8 at 256k context on dual AMD RDNA4 (gfx1201) — working vLLM recipe, audited measurement harness, and the full debugging record
-
Updated
Sep 8, 2026 - Python
A from-scratch LLM inference engine in Zig, specialized for AMD RDNA 4 GPUs.
-
Updated
Sep 11, 2026 - Zig
Extra patches for llama-cpp-rdna-boosts on AMD RDNA4 (gfx1201, Radeon AI PRO R9700): fp8 prefill, faster speculative decoding, and fixes
-
Updated
Nov 22, 2026 - PowerShell
Run PyTorch natively on Windows 11 with an AMD RX 9070 XT (RDNA4 / gfx1201) on stable ROCm 7.2.1 — no WSL2, no Linux, no ZLUDA. Exact pinned wheel URLs, runtime env vars, documented RDNA4 pitfalls (broken nightlies, no xformers/flash-attn/bitsandbytes), and real benchmarks for ComfyUI, SD, LLMs, RVC/TTS. Verified on one 9070 XT.
-
Updated
Jun 16, 2026 - Batchfile
Qwen3.8-27B EXL3 on AMD gfx1201: RX 9070 XT (16 GB, tested) and Radeon AI PRO R9700 (32 GB). vLLM plugin with custom kernels: ~80 tok/s with MTP speculative decoding, int8 KV cache, 32k-64k context on 16 GB (up to 262k on 32 GB), vision and tool calls.
-
Updated
Sep 27, 2026 - Python
Community ROCm 7.2 / RDNA4 gfx1201 patch stack for nvdiffrast. Non-commercial use restrictions may apply; see the NVIDIA Source Code License.
-
Updated
Aug 2, 2026 - Shell
Add this topic to your repo
To associate your repository with the gfx1201 topic, visit your repo's landing page and select "manage topics."