Explain the jargon in the Qwen3.8 post, plus a local LLM glossary - #263
Merged
Conversation
The post leaned on three terms it never defined. Added inline at first use rather than as a glossary box: - Gated DeltaNet: gets its own short paragraph, since the fixed-size recurrent state is what explains the context-flatness numbers later. Plants the mental model early so the 32K and 100K results pay it off. - YaRN: expanded to Yet another RoPE extensioN with a one-line explanation of frequency rescaling. - UD-Q4_K_XL: decoded into its three parts (K-quant super-blocks, Unsloth Dynamic per-layer bit allocation, XL tier promoting selected matrices to 5-bit). Both papers linked: arXiv 2412.06464 and 2309.00071.
Deploying website with
|
| Latest commit: |
1a20030
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://0d651a2e.website-dab.pages.dev |
| Branch Preview URL: | https://qwen38-spark-glossary.website-dab.pages.dev |
Feedback from Shubham was that the post assumes a vocabulary the reader does not have. The sparkrun YAML screenshot was the clearest example: ten settings, no indication of what any of them do or why those values. Inline, in the Qwen3.8 post, because a link out of a post is an escape hatch most readers do not come back from: - A table decoding every line of the sparkrun recipe: what the setting does and why that value, not just what it expands to. - A prefill vs decode primer before the first benchmark table, which also decodes pp2048/tg128 so every table downstream reads cleanly. - The llama.cpp flags (-ngl 99, -c 32768, -fa on) explained where they first appear, and mmproj where the vision path comes up. - NVFP4 deep-linked to Day 4 rather than re-taught. Plus content/blog/local-llm-glossary.md as the reference destination: benchmark reading, why the numbers come out that way, a quant format lookup table, context and KV cache, speed tricks, and copy-paste flag tables for vLLM, llama.cpp, and Ollama. It links out to Days 1-5 instead of duplicating the series, and carries an FAQ block for answer engines. GlossaryNote surfaces it as one compact line under the cover, not a banner: on mobile a banner pushes the article below the fold, which is the exact screen the feedback came from. Tag-gated via lib/glossary.js with a `glossary:` frontmatter override, landing on 13 inference posts. Opted out four where the tags matched but a local-inference glossary is noise (k8sgpt, docker-mcp-catalog, claude-code-leak, tailscale SSH). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
saiyam1814
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Shubham's feedback on the Qwen3.8 post was that it assumes a vocabulary the reader does not have. The sparkrun YAML was the clearest example: ten settings, no indication of what any of them do or why those values.
Inline, in the post
A link out of a post is an escape hatch most readers do not come back from, so the explanations go where the confusion happens.
gpu_memory_utilization,max_model_len,max_num_batched_tokens,load_format: instanttensor,kv_cache_dtype,attention_backend, both parsers, and the Marlin env var.pp2048/tg128so every table downstream reads cleanly.-ngl 99,-c 32768,-fa on) explained where they first appear, andmmprojwhere the vision path comes up.The glossary post
content/blog/local-llm-glossary.md, as the reference destination rather than the primary explanation channel: benchmark reading, why the numbers come out the way they do, a quant format lookup table, context and KV cache, speed tricks, then copy-paste flag tables for vLLM, llama.cpp, and Ollama. It links out to Days 1-5 of the Local LLM series instead of duplicating them, and carries an FAQ block for answer engines. Sketch-style cover generated byscripts/gen-local-llm-glossary-cover.mjs, matching the existing cover scripts.Surfacing it
GlossaryNoterenders one compact line under the cover, not a banner. On mobile a banner pushes the article below the fold, which is the exact screen this feedback came from. Tag-gated vialib/glossary.jswith aglossary:frontmatter override, landing on 13 inference posts. Four are opted out where the tags matched but a local-inference glossary is noise:k8sgpt,docker-mcp-catalog,claude-code-leak, and the Tailscale SSH post.Build passes, 618 pages. The
public/*.xml,llms*.txt,_redirects, andvercel.jsondiffs are prebuild-generated artifacts; they also pick up thenudgebeeentry that was stale on main.🤖 Generated with Claude Code