SuperCharles's Engineering Blog

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT

Home Tags llm-inference

Tag

llm-inference 2

Serving MoE Models: A Deep Dive into Parallelism Strategies (TP, EP, DP) Jun 8, 2026
Where gpu_memory_utilization Actually Goes: vLLM's Memory Budget, Line by Line Jun 4, 2026

Recently Updated

vLLM v1 Deep Dive: How LLM(...) and the Server Boot and Generate
Megatron-LM Fine-Tuning Deep Dive: Qwen Recipes, Datasets, and the Training Loop
Tracing the HuggingFace Trainer Dataloader Path — From `trainer.train()` to a `next(epoch_iterator)`
Fused Linear Cross-Entropy: The Math, the Memory Wall, and Two Ways Around It
GRPO from First Principles, and How verl Implements It

Trending Tags

pytorch gpu cuda vllm distributed-training expert-parallelism kv-cache llm-serving moe torch.compile

© 2026 supercharles. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

pytorch gpu cuda vllm distributed-training expert-parallelism kv-cache llm-serving moe torch.compile

A new version of content is available.