Martin Vit

festr2's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in MiniMaxAI/MiniMax-M2.7 5 days ago

license

👀👍 9

8

#5 opened 5 days ago by

festr2

New activity in festr2/GLM-5-NVFP4-MTP about 1 month ago

[Bug] Eagle V2 speculative decoding crashes with NaN in logits when radix cache prefix hit occurs (SM120 / RTX PRO 6000 Blackwell)

3

#2 opened about 1 month ago by

repandv

Images do not work

1

#1 opened about 1 month ago by

koushd

New activity in nvidia/Qwen3.5-397B-A17B-NVFP4 about 2 months ago

Getting nvidia/Qwen3.5-397B-A17B-NVFP4 running with SGLang (requires transformers v5) on RTX PRO 6000 (blackwell) CUDA 12.9

🔥 1

6

#1 opened about 2 months ago by

bullpoint

New activity in vincentzed-hf/Qwen3.5-397B-A17B-NVFP4 about 2 months ago

Anyone try this on 4x RTX 6000 Pro yet?

52

#1 opened about 2 months ago by

zenmagnets

New activity in lukealonso/MiniMax-M2.5-NVFP4 about 2 months ago

fp8 kv cache

15

#4 opened 2 months ago by

festr2

New activity in Qwen/Qwen3.5-397B-A17B about 2 months ago

fp8

👀 18

6

#5 opened about 2 months ago by

festr2

New activity in mratsim/MiniMax-M2.1-FP8-INT4-AWQ 2 months ago

nvfp4

12

#9 opened 2 months ago by

festr2

New activity in zai-org/GLM-4.7-Flash 3 months ago

FP8 ?

#29 opened 3 months ago by

festr2

New activity in cerebras/GLM-4.7-REAP-268B-A32B-FP8 3 months ago

mtp

4

#1 opened 3 months ago by

festr2

New activity in upstage/Solar-Open-100B 4 months ago

MTP?

1

#5 opened 4 months ago by

festr2

New activity in LGAI-EXAONE/K-EXAONE-236B-A23B 4 months ago

Fp8

1

#1 opened 4 months ago by

festr2

New activity in ArliAI/GLM-4.5-Air-Derestricted-FP8 5 months ago

speculative decoding does not work

#1 opened 5 months ago by

festr2

New activity in ArliAI/README 5 months ago

GLM 4.6

#1 opened 5 months ago by

festr2

New activity in RedHatAI/README 5 months ago

GLM

#3 opened 5 months ago by

festr2

New activity in bullpoint/GLM-4.6-AWQ 6 months ago

GLM-4.6-FP8 - 55 tokens/sec on 4x RTX 6000 PRO

6

#2 opened 6 months ago by

festr2

New activity in RESMP-DEV/GLM-4.6-NVFP4 6 months ago

rtx

14

#1 opened 6 months ago by

festr2

New activity in inclusionAI/Ring-flash-linear-2.0 6 months ago

sglang-0.5.2-py3-none-any.whl

13

#1 opened 7 months ago by

festr2

New activity in inclusionAI/Ring-flash-linear-2.0 7 months ago

sglang-0.5.2-py3-none-any.whl

13

#1 opened 7 months ago by

festr2

sglang-0.5.2-py3-none-any.whl

13

#1 opened 7 months ago by

festr2