正在加载视频...

视频加载失败

返回首页

Hot off the press 🔥 AEON vLLM Ultimate → v0.24.0. Link below ⤵️ The ultimate container for AI on NVIDIA DGX Spark — vLLM compiled from source for GB10/sm_121a. 🔓 UNLOCKED (impossible until this release): ▸ DFlash + FP8 KV cache — 2× KV capacity, draft acceptance intact, measured...

SpaceTimeViking's profile picture

ÆON FORGE ✨

3,542 subscribers

24,800 次观看 • 3 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

"Why are you benchmarking DGX Spark? It's a training box." Yeah. Low bandwidth, but 128GB of unified memory is just sitting there. Plenty of room to optimize. DGX Spark + Qwen3.6 27B. Four backend/quant combos: 🔴 llama.cpp + UD_Q4_K_XL > 11.0 tok/s (baseline), TTFT 297ms 🟢 llama.cpp + DFlash > 20.4 tok/s (peaks at 97 tok/s), TTFT 320ms 🟡 vLLM FP8 + MTP > 13.1 tok/s, TTFT 540ms 🟣 vLLM NVFP4 + MTP > 24.2 tok/s, TTFT 376ms NVFP4+MTP is the winner for me, rock stable around 24 tok/s, no wild swings. DFlash is the wildcard: massive peaks, but fluctuates a lot. FP8+MTP barely beats baseline, and it's FP8. Love my Spark.
3:01

"Why are you benchmarking DGX Spark? It's a training box." Yeah. Low bandwidth, but 128GB of unified memory is just sitting there. Plenty of room to optimize. DGX Spark + Qwen3.6 27B. Four backend/quant combos: 🔴 llama.cpp + UD_Q4_K_XL > 11.0 tok/s (baseline), TTFT 297ms 🟢 llama.cpp + DFlash > 20.4 tok/s (peaks at 97 tok/s), TTFT 320ms 🟡 vLLM FP8 + MTP > 13.1 tok/s, TTFT 540ms 🟣 vLLM NVFP4 + MTP > 24.2 tok/s, TTFT 376ms NVFP4+MTP is the winner for me, rock stable around 24 tok/s, no wild swings. DFlash is the wildcard: massive peaks, but fluctuates a lot. FP8+MTP barely beats baseline, and it's FP8. Love my Spark.

stevibe

40,223 次观看 • 5 个月前

I added KV caching and INT8 KV quantization to our transformer inference, improving throughput by 35x. All of this was done from scratch in Rust + CUDA, on top of a homemade ML framework. On a 4-token prompt with 252 generated tokens: - Original: 0.76 tok/s - KV cache fp32: 27.21 tok/s - KV cache int8 (quantized): 27.29 tok/s Try it out yourself here: In practice: - KV caching gave us about a 35x end-to-end speedup - INT8 KV cache kept roughly the same speed as fp32 but cut KV cache memory by 3.78x FP32 cache used 4.5 MB in this run while the INT8 cache used only 1.19 MB This simple change to inference created a huge impact on performance. To learn more about the KV cache and other optimizations like this, check out the blog at
2:36

I added KV caching and INT8 KV quantization to our transformer inference, improving throughput by 35x. All of this was done from scratch in Rust + CUDA, on top of a homemade ML framework. On a 4-token prompt with 252 generated tokens: - Original: 0.76 tok/s - KV cache fp32: 27.21 tok/s - KV cache int8 (quantized): 27.29 tok/s Try it out yourself here: In practice: - KV caching gave us about a 35x end-to-end speedup - INT8 KV cache kept roughly the same speed as fp32 but cut KV cache memory by 3.78x FP32 cache used 4.5 MB in this run while the INT8 cache used only 1.19 MB This simple change to inference created a huge impact on performance. To learn more about the KV cache and other optimizations like this, check out the blog at

Reese Chong

53,026 次观看 • 5 个月前

One DGX Spark. Qwen3.6-35B 64 users. 700+ tok/s. 32,768 tokens in 54 seconds. 38W Each user has their own prompt and their own KV cache, and vLLM batches every active stream through the GPU each step. Recipe → NVIDIA AI
1:06

One DGX Spark. Qwen3.6-35B 64 users. 700+ tok/s. 32,768 tokens in 54 seconds. 38W Each user has their own prompt and their own KV cache, and vLLM batches every active stream through the GPU each step. Recipe → NVIDIA AI

Wësche

165,819 次观看 • 3 个月前

Did you know Qwen 3.6 35B NVFP4 with 256k context, MTP, kv cache fp16 & image support takes around 68gb of VRAM? My NVIDIA AI DGX Spark can do 110 tok/s 👇
0:31

Did you know Qwen 3.6 35B NVFP4 with 256k context, MTP, kv cache fp16 & image support takes around 68gb of VRAM? My NVIDIA AI DGX Spark can do 110 tok/s 👇

Mia

35,255 次观看 • 3 个月前

DFlash speculative decoding on Apple Silicon Qwen3.5-9B bf16 · M5 Max · greedy exact match ▸ 85 tok/s, 3.3× at 1024 tokens (runtime) ▸ ~70 tok/s, 2.6× in the video (terminal I/O overhead) ▸ 80 tok/s, 3.1× at 2048 tokens (runtime) Currently working on: → Long context (speedup degrades past 4K tokens, KV cache growth) → Int4 quantized models (27B class) Built on MLX, no CUDA, single machine. Draft generates 16 tokens in parallel, target verifies in one forward pass. Will open source when ready.
0:39

DFlash speculative decoding on Apple Silicon Qwen3.5-9B bf16 · M5 Max · greedy exact match ▸ 85 tok/s, 3.3× at 1024 tokens (runtime) ▸ ~70 tok/s, 2.6× in the video (terminal I/O overhead) ▸ 80 tok/s, 3.1× at 2048 tokens (runtime) Currently working on: → Long context (speedup degrades past 4K tokens, KV cache growth) → Int4 quantized models (27B class) Built on MLX, no CUDA, single machine. Draft generates 16 tokens in parallel, target verifies in one forward pass. Will open source when ready.

bstn 👁️

37,049 次观看 • 6 个月前

i spent 3 hours finding the sweet spot for hermes 4.3 36B on a single RTX 3090. saving you the trouble, anon. the model is 21.8GB at Q4_K_M. that leaves 2.2GB free on 24GB VRAM. not much room for KV cache. here's what actually happened: 4K: 35.3 tok/s 8K: 35.2 tok/s 16K: 34.8 tok/s 32K: 34.6 tok/s 64K: 6.4 tok/s 128K: 1.9 tok/s flat from 4K to 32K. then it falls off a cliff at 64K. the trick is quantized KV cache. without it you OOM at 16K. with quantized KV cache you get 32K at full speed. all 64 layers on GPU. at 64K something weird happens. ngl 99 (all layers on GPU) = 3.96 tok/s. the KV cache silently spills to CPU. drop to ngl 55 and speed jumps to 6.37. drop to ngl 48 and it gets worse again (3.46). there's an offload sweet spot where you free just enough VRAM for the cache without losing too much compute to PCIe transfers. 128K works at ngl 32 but you're at 1.95 tok/s. half the model on CPU. usable for batch work, not for interactive. the sweet spot command: llama-server -m hermes-4.3-36b-Q4_K_M.gguf -ngl 99 -c 32768 --cache-type-k q4_0 --cache-type-v q4_0 32K context. 34.6 tok/s. all on GPU. this is where dense 36B lives on 24GB. for comparison, qwen 3.5 (35B MoE, 3B active) holds 112 tok/s from 4K all the way to 262K on the same GPU. no speed drop. same total params, completely different architecture. hybrid linear attention means flat context scaling. dense pays for every token in the KV cache. code and quality comparison coming next. fast vs slow generation side by side in the videos below.
2:29

i spent 3 hours finding the sweet spot for hermes 4.3 36B on a single RTX 3090. saving you the trouble, anon. the model is 21.8GB at Q4_K_M. that leaves 2.2GB free on 24GB VRAM. not much room for KV cache. here's what actually happened: 4K: 35.3 tok/s 8K: 35.2 tok/s 16K: 34.8 tok/s 32K: 34.6 tok/s 64K: 6.4 tok/s 128K: 1.9 tok/s flat from 4K to 32K. then it falls off a cliff at 64K. the trick is quantized KV cache. without it you OOM at 16K. with quantized KV cache you get 32K at full speed. all 64 layers on GPU. at 64K something weird happens. ngl 99 (all layers on GPU) = 3.96 tok/s. the KV cache silently spills to CPU. drop to ngl 55 and speed jumps to 6.37. drop to ngl 48 and it gets worse again (3.46). there's an offload sweet spot where you free just enough VRAM for the cache without losing too much compute to PCIe transfers. 128K works at ngl 32 but you're at 1.95 tok/s. half the model on CPU. usable for batch work, not for interactive. the sweet spot command: llama-server -m hermes-4.3-36b-Q4_K_M.gguf -ngl 99 -c 32768 --cache-type-k q4_0 --cache-type-v q4_0 32K context. 34.6 tok/s. all on GPU. this is where dense 36B lives on 24GB. for comparison, qwen 3.5 (35B MoE, 3B active) holds 112 tok/s from 4K all the way to 262K on the same GPU. no speed drop. same total params, completely different architecture. hybrid linear attention means flat context scaling. dense pays for every token in the KV cache. code and quality comparison coming next. fast vs slow generation side by side in the videos below.

Sudo su

52,268 次观看 • 7 个月前

We’re thrilled to open-source TriAttention! 🚀 🦞 Deploy OpenClaw (32B LLM) on a single 24GB RTX 4090 locally 💻Full code open-source & vLLM-ready for one-click deployment ⚡️ 2.5× faster inference speed & 10.7× less KV cache memory usage TriAttention is a novel KV cache compression method built on rigorous trigonometric analysis in the Pre‑RoPE space for efficient LLM long reasoning. Github Repo: Paper Link: Homepage:
0:28

We’re thrilled to open-source TriAttention! 🚀 🦞 Deploy OpenClaw (32B LLM) on a single 24GB RTX 4090 locally 💻Full code open-source & vLLM-ready for one-click deployment ⚡️ 2.5× faster inference speed & 10.7× less KV cache memory usage TriAttention is a novel KV cache compression method built on rigorous trigonometric analysis in the Pre‑RoPE space for efficient LLM long reasoning. Github Repo: Paper Link: Homepage:

Yukang Chen

199,279 次观看 • 6 个月前

I just crammed the updated Gemma 4 26B A4B QAT (MoE) with 180k context into an 8GB RTX 4060 (8 GB VRAM + 16 GB RAM only!!) and optimized the batch size. 23 tokens/sec decode, 300 tokens/sec prefill Yesterday I showed you a Gemma 4 31B dense model running flawlessly on an RTX 4090. Today, we're breaking the VRAM bank on a budget card using Unsloth’s new Gemma 4 26B (A4B) QAT quants. Following Google’s chat template update that boosted agentic benchmarks by +10%, I pushed this model to its absolute limits. Here is how you squeeze 250k context out of 8GB of VRAM. # The Setup & The Optimization - Hardware: Nvidia RTX 4060 (8GB VRAM) + 16GB System RAM - Environment: CUDA 13.0 build of llama.cpp - Model: gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf - Prompt: 28,000 tokens of prompt for each run If you read my L2 cache breakdown (attached in replies), you know the 4060’s 24MB cache maxes out at `-b 1024 -ub 1024`. Push past that, and prefill crashes. I locked those flags in for every test below to ensure maximum GEMM throughput. # 1. The Raw Context Push (Unquantized KV Cache) First, I wanted to see how far pure 8GB VRAM + 16GB RAM could stretch without touching the KV cache: - 80k Context: Prefill 385 t/s | Decode 25.5 t/s - 120k Context: Prefill 270 t/s | Decode 24 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 120000 --port 8080 -ub 1024 -b 1024 Without KV quantization, 120k is your hard ceiling. push past that prefill throughput drops off a cliff, making the model practically unusable for large agentic workloads. # 2. The Q8 KV Cache Lifeline To survive 250k context on a budget card, you have to quantize the KV cache. I enabled 8 bit KV cache (`-ctk q8_0 -ctv q8_0`) and re ran: - 180k Context: Prefill 280 t/s | Decode 22.8 t/s - 250k Context: Prefill 115 t/s | Decode 20 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 180000 --port 8080 -b 1024 -ub 1024 -ctk q8_0 -ctv q8_0 Result: Q8 KV cache brings 250k context back from the dead. Decode speed stabilizes at a highly usable 20 t/s. You are trading a very small bit amount of reasoning precision for an extra 130,000 tokens of context window. if you own a single rtx 3050, 3060, 3070, 4050, 4060, 5050 or 5060, you must try this model and optimize your batch size for higher prefill. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. What model are you running on your 6GB, 8GB or 12GB cards right now? Let's see your setups.
0:20

I just crammed the updated Gemma 4 26B A4B QAT (MoE) with 180k context into an 8GB RTX 4060 (8 GB VRAM + 16 GB RAM only!!) and optimized the batch size. 23 tokens/sec decode, 300 tokens/sec prefill Yesterday I showed you a Gemma 4 31B dense model running flawlessly on an RTX 4090. Today, we're breaking the VRAM bank on a budget card using Unsloth’s new Gemma 4 26B (A4B) QAT quants. Following Google’s chat template update that boosted agentic benchmarks by +10%, I pushed this model to its absolute limits. Here is how you squeeze 250k context out of 8GB of VRAM. # The Setup & The Optimization - Hardware: Nvidia RTX 4060 (8GB VRAM) + 16GB System RAM - Environment: CUDA 13.0 build of llama.cpp - Model: gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf - Prompt: 28,000 tokens of prompt for each run If you read my L2 cache breakdown (attached in replies), you know the 4060’s 24MB cache maxes out at `-b 1024 -ub 1024`. Push past that, and prefill crashes. I locked those flags in for every test below to ensure maximum GEMM throughput. # 1. The Raw Context Push (Unquantized KV Cache) First, I wanted to see how far pure 8GB VRAM + 16GB RAM could stretch without touching the KV cache: - 80k Context: Prefill 385 t/s | Decode 25.5 t/s - 120k Context: Prefill 270 t/s | Decode 24 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 120000 --port 8080 -ub 1024 -b 1024 Without KV quantization, 120k is your hard ceiling. push past that prefill throughput drops off a cliff, making the model practically unusable for large agentic workloads. # 2. The Q8 KV Cache Lifeline To survive 250k context on a budget card, you have to quantize the KV cache. I enabled 8 bit KV cache (`-ctk q8_0 -ctv q8_0`) and re ran: - 180k Context: Prefill 280 t/s | Decode 22.8 t/s - 250k Context: Prefill 115 t/s | Decode 20 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 180000 --port 8080 -b 1024 -ub 1024 -ctk q8_0 -ctv q8_0 Result: Q8 KV cache brings 250k context back from the dead. Decode speed stabilizes at a highly usable 20 t/s. You are trading a very small bit amount of reasoning precision for an extra 130,000 tokens of context window. if you own a single rtx 3050, 3060, 3070, 4050, 4060, 5050 or 5060, you must try this model and optimize your batch size for higher prefill. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. What model are you running on your 6GB, 8GB or 12GB cards right now? Let's see your setups.

Alok

36,617 次观看 • 2 个月前

Ran Google’s cookbook with 10 agents on my tiny GB10 GPU. 436 tok/s / 43.6 per agent Qwen3.6-35B + Dflash + DDTree on vLLM GB10 @ 74W The future isn't 10,000 GPUs in a nuclear-powered data center. It’s 10 agents on your desk solving your problems while you make your coffee.
2:02

Ran Google’s cookbook with 10 agents on my tiny GB10 GPU. 436 tok/s / 43.6 per agent Qwen3.6-35B + Dflash + DDTree on vLLM GB10 @ 74W The future isn't 10,000 GPUs in a nuclear-powered data center. It’s 10 agents on your desk solving your problems while you make your coffee.

Mitko Vasilev

146,830 次观看 • 5 个月前

DFlash 2 is here! Qwen3.8-27B at 70 tok/s on an M5 Max MacBook Pro. ⚡ Up to 4.6× the speed of autoregressive decoding, with the same output. This is the next generation of DFlash, seeded at Z Lab and upgraded at Inco AI. Get one more accepted token on every pass, for free!
0:26

DFlash 2 is here! Qwen3.8-27B at 70 tok/s on an M5 Max MacBook Pro. ⚡ Up to 4.6× the speed of autoregressive decoding, with the same output. This is the next generation of DFlash, seeded at Z Lab and upgraded at Inco AI. Get one more accepted token on every pass, for free!

Zhijian Liu

1,161,878 次观看 • 1 个月前

Run Updated Gemma 4 26B A4B QAT (MoE) with Vision at 25 tokens/sec and massive 120k context window on a single RTX 4060 (8 GB VRAM + 16 GB RAM Only!!) Yesterday I pushed Gemma 4 26B A4B QAT to 250k context on a single RTX 4060 using nothing but Q8 KV cache and optimized -b and -ub flags for higher prefill throughput. Today I stacked Multi Token Prediction (MTP) self speculative decoding AND the vision projector (mmproj) on top of that same card, same batch size optimization, same $250 GPU and pushed it until it broke, then found the fix. All text only runs consist of a 28k prompt. vision runs consist of 28k text prompt + an image. # 1. MTP alone. near free decode speed, no catch MTP draft assistant is a separate small model (MTP heads are backed into the main model itself for the qwen 3.5+ models but its a separate small model for gemma 4 series), 240 MB gguf 80k ctx: Prefill 510 t/s | Decode 29.5 t/s 120k ctx: Prefill 433 t/s | Decode 29 t/s 180k ctx: Prefill 240 t/s | Decode 24.9 t/s 250k ctx: Prefill 63 t/s | Decode 13 t/s llama.cpp flags: m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf-c 180000 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 # 2. Add vision on top. the tax you actually pay the vision projector gguf is about 1.1 GBs 80k ctx: Prefill 360 t/s | Decode 25.4 t/s 120k ctx: Prefill 230 t/s | Decode 23.8 t/s 180k ctx (Q8 KV): Prefill 75 t/s | Decode 12.5 t/s - cliff flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf -c 80000 --port 8080 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 --mmproj mmproj-F16.gguf # 3. The fix if you want to run vision over 120k context: swap Q8 KV for Q4 KV past 120k Stack MTP + vision + Q8 KV past 120k context and you hit a wall. draft model overhead plus KV pressure tanks everything. Drop to Q4 KV and the wall disappears: 180k ctx (Q4 KV): Prefill 220 t/s | Decode 25.5 t/s -ctk q4_0 -ctv q4_0 --mmproj mmproj-F16.gguf (rest same as above) Bottom line: MTP gives you a near free +20-30% decode boost up to 120k context. Past that, it's fighting your VRAM, not helping and if vision is loaded too, Q4 KV isn't optional past 120k, it's mandatory. 30% boost is model and card specific, MTP boosted decode 2x for gemma 4 31b on a single rtx 4090. Same 8GB card. Same $250 GPU. Multimodal, speculative decoding, 180k usable context, zero upgrades. You gotta try this if you have a single NVIDIA RTX 3050, 3060, 3070, 4050, 4060, 5050 or 5060. You can try it with a 6 GB VRAM card as well but you will have to lower the context window. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. Which models are you running on your 6/8/12GB cards with MTP?
0:20

Run Updated Gemma 4 26B A4B QAT (MoE) with Vision at 25 tokens/sec and massive 120k context window on a single RTX 4060 (8 GB VRAM + 16 GB RAM Only!!) Yesterday I pushed Gemma 4 26B A4B QAT to 250k context on a single RTX 4060 using nothing but Q8 KV cache and optimized -b and -ub flags for higher prefill throughput. Today I stacked Multi Token Prediction (MTP) self speculative decoding AND the vision projector (mmproj) on top of that same card, same batch size optimization, same $250 GPU and pushed it until it broke, then found the fix. All text only runs consist of a 28k prompt. vision runs consist of 28k text prompt + an image. # 1. MTP alone. near free decode speed, no catch MTP draft assistant is a separate small model (MTP heads are backed into the main model itself for the qwen 3.5+ models but its a separate small model for gemma 4 series), 240 MB gguf 80k ctx: Prefill 510 t/s | Decode 29.5 t/s 120k ctx: Prefill 433 t/s | Decode 29 t/s 180k ctx: Prefill 240 t/s | Decode 24.9 t/s 250k ctx: Prefill 63 t/s | Decode 13 t/s llama.cpp flags: m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf-c 180000 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 # 2. Add vision on top. the tax you actually pay the vision projector gguf is about 1.1 GBs 80k ctx: Prefill 360 t/s | Decode 25.4 t/s 120k ctx: Prefill 230 t/s | Decode 23.8 t/s 180k ctx (Q8 KV): Prefill 75 t/s | Decode 12.5 t/s - cliff flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf -c 80000 --port 8080 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 --mmproj mmproj-F16.gguf # 3. The fix if you want to run vision over 120k context: swap Q8 KV for Q4 KV past 120k Stack MTP + vision + Q8 KV past 120k context and you hit a wall. draft model overhead plus KV pressure tanks everything. Drop to Q4 KV and the wall disappears: 180k ctx (Q4 KV): Prefill 220 t/s | Decode 25.5 t/s -ctk q4_0 -ctv q4_0 --mmproj mmproj-F16.gguf (rest same as above) Bottom line: MTP gives you a near free +20-30% decode boost up to 120k context. Past that, it's fighting your VRAM, not helping and if vision is loaded too, Q4 KV isn't optional past 120k, it's mandatory. 30% boost is model and card specific, MTP boosted decode 2x for gemma 4 31b on a single rtx 4090. Same 8GB card. Same $250 GPU. Multimodal, speculative decoding, 180k usable context, zero upgrades. You gotta try this if you have a single NVIDIA RTX 3050, 3060, 3070, 4050, 4060, 5050 or 5060. You can try it with a 6 GB VRAM card as well but you will have to lower the context window. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. Which models are you running on your 6/8/12GB cards with MTP?

Alok

16,434 次观看 • 2 个月前

Red Hat AI just shipped DFlash speculator checkpoints for two of NVIDIA AI's most powerful open models: → Nemotron Ultra 550B → Nemotron Super 120B On math and reasoning: ~5 out of 7 draft tokens accepted on average. On code (HumanEval): ~3.4 out of 7. Both checkpoints trained with the open source Speculators library from vLLM. Apache 2.0. Validated on NVIDIA B200. One flag to enable in vLLM: --spec-model RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-speculator.dflash --spec-tokens 7 --spec-method dflash 🔗 Ultra 550B: 🔗 Super 120B:
0:32

Red Hat AI just shipped DFlash speculator checkpoints for two of NVIDIA AI's most powerful open models: → Nemotron Ultra 550B → Nemotron Super 120B On math and reasoning: ~5 out of 7 draft tokens accepted on average. On code (HumanEval): ~3.4 out of 7. Both checkpoints trained with the open source Speculators library from vLLM. Apache 2.0. Validated on NVIDIA B200. One flag to enable in vLLM: --spec-model RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-speculator.dflash --spec-tokens 7 --spec-method dflash 🔗 Ultra 550B: 🔗 Super 120B:

Red Hat AI

15,077 次观看 • 2 个月前

Google's Gemma 4 26B A4B QAT hits 25+ tokens/sec and 320+ tokens/sec prefill on 8 GB VRAM (RTX 4060) + 16 GB RAM using TurboQuant Prefill just went from 200 → 320+ tok/s on the same 8GB card. 1.6x, no new hardware, no new quant, just a KV cache trick stacked on top of the Gemma 4 26B MoE setup from a few days ago. A few days ago I posted Gemma 4 26B A4B hitting 28 tok/s decode on 8GB VRAM using native MTP. prefill was stuck around 200 tok/s. fair callout by the community. So today I tested something I'd already been meaning to try: TheTom/llama-cpp-turboquant, the TurboQuant KV cache fork by Tom Turney (Tom Turney). (github link in the comments) thanks to him, the fork just got resynced to mainline, so MTP + TurboQuant now run together cleanly (I didnt see any meaningful gains by using MTP with this setup though but you can try). The flags (No MTP): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -cnv -c 64000 --cache-type-k q8_0 --cache-type-v turbo3 Results on the same RTX 4060 8GB, tested with a 27k token prompt at 64k context loaded: Prefill: 200 tok/s → 320+ tok/s Decode: stayed above 25 tok/s (without MTP) Why it works: TurboQuant uses walsh hadamard rotation + polar quantization on the KV cache. keys are sensitive to compression, values aren't much, so it splits the difference: K stays at q8_0, V drops to turbo3 (~3 bits). bonus from the memory savings: same 8GB card can now stretch to 100-120k context with minimal decode penalty. It should now be snappier with any agent harness such as hermes agent without compromise on intelligence. If you're already running Gemma 4 on a small card, this stacks on top for free. Try --cache-type-k q8_0 --cache-type-v turbo3 on your setup and report back what your prefill/decode split looks like. unsloth model gguf and llama.cpp turboquant fork links in the comments. what's your prefill number before vs after?
0:31

Google's Gemma 4 26B A4B QAT hits 25+ tokens/sec and 320+ tokens/sec prefill on 8 GB VRAM (RTX 4060) + 16 GB RAM using TurboQuant Prefill just went from 200 → 320+ tok/s on the same 8GB card. 1.6x, no new hardware, no new quant, just a KV cache trick stacked on top of the Gemma 4 26B MoE setup from a few days ago. A few days ago I posted Gemma 4 26B A4B hitting 28 tok/s decode on 8GB VRAM using native MTP. prefill was stuck around 200 tok/s. fair callout by the community. So today I tested something I'd already been meaning to try: TheTom/llama-cpp-turboquant, the TurboQuant KV cache fork by Tom Turney (Tom Turney). (github link in the comments) thanks to him, the fork just got resynced to mainline, so MTP + TurboQuant now run together cleanly (I didnt see any meaningful gains by using MTP with this setup though but you can try). The flags (No MTP): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -cnv -c 64000 --cache-type-k q8_0 --cache-type-v turbo3 Results on the same RTX 4060 8GB, tested with a 27k token prompt at 64k context loaded: Prefill: 200 tok/s → 320+ tok/s Decode: stayed above 25 tok/s (without MTP) Why it works: TurboQuant uses walsh hadamard rotation + polar quantization on the KV cache. keys are sensitive to compression, values aren't much, so it splits the difference: K stays at q8_0, V drops to turbo3 (~3 bits). bonus from the memory savings: same 8GB card can now stretch to 100-120k context with minimal decode penalty. It should now be snappier with any agent harness such as hermes agent without compromise on intelligence. If you're already running Gemma 4 on a small card, this stacks on top for free. Try --cache-type-k q8_0 --cache-type-v turbo3 on your setup and report back what your prefill/decode split looks like. unsloth model gguf and llama.cpp turboquant fork links in the comments. what's your prefill number before vs after?

Alok

119,821 次观看 • 3 个月前

Mirai Labs (Mirai Labs) compressed Qwen3.8-27B to 2.4 bits. I ported it to llama.cpp and now it runs on a 12 GB card with 128K context. With q4 KV cache the 128K window takes 11.3 GB of VRAM, with q8 KV you get 74K in 11.1 GB. Decode is 40 tok/s, still 34-35 tok/s at 62K deep, and prefill around 1000 tok/s. I measured all of it on 1 RTX 3090 at 300 W, capped to what fits in 12 GB. No requant anywhere. The GGUF carries Mirai's compressed codes bit for bit, and greedy output matches their own vLLM plugin. Everything in the video was built by this same model as an agent in pi, 11 builds from 1 prompt each, a few needed a follow up and 1 is a blooper. That run was vLLM on my 3090s. Today the same weights run in llama.cpp. Big thread, all links and recipes 👇
2:37

Mirai Labs (Mirai Labs) compressed Qwen3.8-27B to 2.4 bits. I ported it to llama.cpp and now it runs on a 12 GB card with 128K context. With q4 KV cache the 128K window takes 11.3 GB of VRAM, with q8 KV you get 74K in 11.1 GB. Decode is 40 tok/s, still 34-35 tok/s at 62K deep, and prefill around 1000 tok/s. I measured all of it on 1 RTX 3090 at 300 W, capped to what fits in 12 GB. No requant anywhere. The GGUF carries Mirai's compressed codes bit for bit, and greedy output matches their own vLLM plugin. Everything in the video was built by this same model as an agent in pi, 11 builds from 1 prompt each, a few needed a follow up and 1 is a blooper. That run was vLLM on my 3090s. Today the same weights run in llama.cpp. Big thread, all links and recipes 👇

Alexey Fateev

31,679 次观看 • 12 天前

Ex-vLLM core contributor explained how to make LLM inference 10x cheaper in 34 minutes - better than $3000 inference optimization bootcamps. request comes in -> check LMCache -> hit? load KV cache from CPU/SSD/remote -> skip prefill -> serve. That loop is why Bloomberg and other production stacks now push 300 terabytes of KV cache per week. LMCache + vLLM + CPU/SSD/remote storage + zero-copy CUDA kernels - that's the stack. Watch and save it, then wire the KV-offload into your inference stack.
34:46

Ex-vLLM core contributor explained how to make LLM inference 10x cheaper in 34 minutes - better than $3000 inference optimization bootcamps. request comes in -> check LMCache -> hit? load KV cache from CPU/SSD/remote -> skip prefill -> serve. That loop is why Bloomberg and other production stacks now push 300 terabytes of KV cache per week. LMCache + vLLM + CPU/SSD/remote storage + zero-copy CUDA kernels - that's the stack. Watch and save it, then wire the KV-offload into your inference stack.

h100envy

61,470 次观看 • 2 个月前

Recent KV cache compression research has focused on small models with dense attention. We scaled these techniques to GLM 5.3, a frontier sparse attention model. We adapted KVzip and Attention Matching, reducing KV cache size by 80% while retaining over 90% of full-context accuracy on the QuALITY benchmark.
1:14

Recent KV cache compression research has focused on small models with dense attention. We scaled these techniques to GLM 5.3, a frontier sparse attention model. We adapted KVzip and Attention Matching, reducing KV cache size by 80% while retaining over 90% of full-context accuracy on the QuALITY benchmark.

Ramp Labs

18,884 次观看 • 10 天前

Splash is here! A month ago, DFlash 2 ran Qwen3.8-27B at 70 tok/s on an M5 Max. Today, Splash runs it at 144 tok/s on the same Mac ⚡ Getting that speed used to take work. Splash is built around the model, with the DFlash 2 draft already in it. Two commands and you're running.
0:26

Splash is here! A month ago, DFlash 2 ran Qwen3.8-27B at 70 tok/s on an M5 Max. Today, Splash runs it at 144 tok/s on the same Mac ⚡ Getting that speed used to take work. Splash is built around the model, with the DFlash 2 draft already in it. Two commands and you're running.

Zhijian Liu

92,333 次观看 • 20 天前

DFlash v0.1.4 : custom Metal verify kernels for quantized Qwen3 hybrid models, plus significant peak memory reduction at long context. M5 Max 40-core GPU, 64GB, stock mlx_lm baseline: Qwen3.6-35B-A3B-4bit: ► @ 1024 · 138.3 → 300.3 tok/s (2.20x) ► @ 2048 · 135.6 → 246.4 tok/s (1.81x) ► @ 4096 · 134.5 → 208.4 tok/s (1.56x) ► @ 8192 · 133.2 → 177.4 tok/s (1.33x) Qwen3.5-27B-4bit: ► @ 1024 · 33.5 → 79.0 tok/s (2.37x) ► @ 2048 · 33.1 → 70.2 tok/s (2.12x) ► @ 4096 · 31.5 → 55.7 tok/s (1.77x) ► @ 8192 · 33.9 → 45.3 tok/s (1.34x) Working on making this usable for agentic workloads goal is to never drop below baseline at any context depth. LLM decode is memory-bandwidth bound. M5 Max runs at 614 GB/s, that's 1.5x more than M1-M4 Max (400-410 GB/s). Results will vary on lower bandwidth chips.
0:32

DFlash v0.1.4 : custom Metal verify kernels for quantized Qwen3 hybrid models, plus significant peak memory reduction at long context. M5 Max 40-core GPU, 64GB, stock mlx_lm baseline: Qwen3.6-35B-A3B-4bit: ► @ 1024 · 138.3 → 300.3 tok/s (2.20x) ► @ 2048 · 135.6 → 246.4 tok/s (1.81x) ► @ 4096 · 134.5 → 208.4 tok/s (1.56x) ► @ 8192 · 133.2 → 177.4 tok/s (1.33x) Qwen3.5-27B-4bit: ► @ 1024 · 33.5 → 79.0 tok/s (2.37x) ► @ 2048 · 33.1 → 70.2 tok/s (2.12x) ► @ 4096 · 31.5 → 55.7 tok/s (1.77x) ► @ 8192 · 33.9 → 45.3 tok/s (1.34x) Working on making this usable for agentic workloads goal is to never drop below baseline at any context depth. LLM decode is memory-bandwidth bound. M5 Max runs at 614 GB/s, that's 1.5x more than M1-M4 Max (400-410 GB/s). Results will vary on lower bandwidth chips.

bstn 👁️

23,120 次观看 • 5 个月前

DFlash makes Qwen 2.2x faster with no quality loss! We ran the same Qwen3.6-27B locally three ways on one RTX 6000: baseline, MTP, DFlash. The tasks only differ in one thing - how predictable the next word is: quicksort, describe a file in JSON, a logic puzzle, a sci-fi story. Outputs: Baseline: 44 tok/s · 1.00x MTP: 65 tok/s · 1.45x · 71% accepted DFlash: 98 tok/s · 2.20x · 30% accepted Baseline writes one token per step. MTP works inside the model itself and guesses 3 tokens ahead. DFlash is a separate small model that writes 15 tokens at once, and the big model only checks them. In JSON the same words repeat all the time, so most guesses were right: 152 tok/s, 3.4x speedup. In the story 9 guesses out of 10 were wrong. DFlash did all that extra work for nothing and became slower than baseline: 42 vs 44 tok/s. MTP guesses only 3 tokens, so a wrong guess costs very little: 46 tok/s and the win in that round. The output is identical in all three modes - DFlash is the pick for tasks with predictable output, like coding, and for chat and creative writing MTP works better. DFlash is now natively integrated into Atomic Chat on llama.cpp - speed up your Qwen models!
0:26

DFlash makes Qwen 2.2x faster with no quality loss! We ran the same Qwen3.6-27B locally three ways on one RTX 6000: baseline, MTP, DFlash. The tasks only differ in one thing - how predictable the next word is: quicksort, describe a file in JSON, a logic puzzle, a sci-fi story. Outputs: Baseline: 44 tok/s · 1.00x MTP: 65 tok/s · 1.45x · 71% accepted DFlash: 98 tok/s · 2.20x · 30% accepted Baseline writes one token per step. MTP works inside the model itself and guesses 3 tokens ahead. DFlash is a separate small model that writes 15 tokens at once, and the big model only checks them. In JSON the same words repeat all the time, so most guesses were right: 152 tok/s, 3.4x speedup. In the story 9 guesses out of 10 were wrong. DFlash did all that extra work for nothing and became slower than baseline: 42 vs 44 tok/s. MTP guesses only 3 tokens, so a wrong guess costs very little: 46 tok/s and the win in that round. The output is identical in all three modes - DFlash is the pick for tasks with predictable output, like coding, and for chat and creative writing MTP works better. DFlash is now natively integrated into Atomic Chat on llama.cpp - speed up your Qwen models!

atomic.chat

83,196 次观看 • 2 个月前

got k2 thinking working on vllm completely maxxing out vram on 8xH100 i span up. had to quantize the kv cache to fp8 and decrease seq len to 1024 or else it would OOM. this is not sped up (~3.0 toks/sec). this took about 2 hrs of tweaking serving settings. livestreaming this rn
0:20

got k2 thinking working on vllm completely maxxing out vram on 8xH100 i span up. had to quantize the kv cache to fp8 and decrease seq len to 1024 or else it would OOM. this is not sped up (~3.0 toks/sec). this took about 2 hrs of tweaking serving settings. livestreaming this rn

Elliot Arledge

39,295 次观看 • 11 个月前