row/SPEC-DECODE-INVENTORY: full vLLM speculator enumeration + 9 roadmap rows - #53
Closed
localai-bot wants to merge 2 commits into
Closed
row/SPEC-DECODE-INVENTORY: full vLLM speculator enumeration + 9 roadmap rows#53localai-bot wants to merge 2 commits into
localai-bot wants to merge 2 commits into
Conversation
…9 gaps rowed INVENTORIED
Enumerate ALL speculative-decoding methods supported by pinned vLLM 555967922
(0.26.0.dev0) from SOURCE, cross-reference our support, and row every gap.
- New master inventory `.agents/specs/spec-decode-inventory.md`: 13 vLLM
SpeculativeMethod strings + acceptance/draft-sample/dynamic-k config axes,
each x {upstream anchor, V1 status, our status}. Key findings: mlp_speculator
has NO V1 proposer (dispatch ValueError) = upstream-deprecated; dflash/dspark
are REAL vLLM methods (our DFlash mirrors vLLM, not ours-beyond).
- 9 new engine-matrix rows (INVENTORIED, value-ordered): SPEC-NGRAM-GPU,
SPEC-SUFFIX, SPEC-EAGLE, SPEC-MTP-FAMILY, SPEC-ACCEPT-VARIANTS, SPEC-DYNAMIC,
SPEC-CUSTOM-CLASS, SPEC-EXTRACT-HIDDEN, SPEC-MLP-SPECULATOR. ENGINE_ROWS
131->140; engine summary Total + area rows updated.
- roadmap ROAD-V1-D3 + gap paragraph enumerate the nine; FEATURES spec rows
corrected (Medusa CPU-brick->spike drift fixed, n-gram ->DONE, EAGLE->EAGLE1/3,
+breadth row); BENCHMARKS spec table +ngram +breadth rows.
- STATUS method-surface paragraph added, PAID by collapsing 4 superseded
DeepSeek-V4 decode-lever paragraphs (dup in BENCHMARKS, superseded by the
1.14x BEATS-ds4 binding) = -5772 chars; STATUS_RATCHET 287838->282066.
- Records-only, no C++. check-agent-record / doc-checkpoint / public-doc-tables
/ now-current / state-order all green.
FOLLOWING_AGENTS_PROTOCOL
Assisted-by: Claude Code:claude-opus-4-8 [ClaudeCode]
# Conflicts: # .agents/state.md # scripts/check-public-doc-tables.py
Collaborator
Author
|
Landed on main as the squash (mudler authorship). 🤖 Generated with Claude Code |
mudler
added a commit
that referenced
this pull request
Aug 6, 2026
#53) row/SPEC-DECODE-INVENTORY squash, records-only (USER-directed). 13 methods enumerated from the pinned source with anchors + V1 status; coverage cross-referenced against code (ngram/MTP/DFlash DONE, draft_model ACTIVE, medusa spike-only with the FEATURES drift corrected, DeepSeek-V4 MTP weight-blocked by the GGUF converter dropping nextn). 9 new INVENTORIED rows: SPEC-NGRAM-GPU, SPEC-SUFFIX, SPEC-EAGLE, SPEC-MTP-FAMILY, SPEC-ACCEPT-VARIANTS, SPEC-DYNAMIC, SPEC-CUSTOM-CLASS, SPEC-EXTRACT-HIDDEN, SPEC-MLP-SPECULATOR (upstream-deprecated). Upstream find: mlp_speculator enum-accepted but V1-dispatch-dead. Master table .agents/specs/spec-decode-inventory.md; STATUS compacted, ratchet 287,832->284,329. FOLLOWING_AGENTS_PROTOCOL Assisted-by: Claude Code:claude-opus-4-8 [ClaudeCode]
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
2 participants
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.
USER-directed. 13 spec-decode methods enumerated from the pinned vLLM SOURCE (config enum, V1 dispatch, MRV2 factory, proposers, speculator models, HF speculators formats) with file:line anchors and upstream-V1 status. Our coverage cross-referenced against CODE: ngram DONE (27B 5/5 strict), MTP DONE (both gate models), DFlash DONE (a REAL vLLM method our port mirrors - framing corrected), draft_model ACTIVE (CPU brick), medusa SPIKE-only (FEATURES drift ◐ -> ☐ corrected), DeepSeek-V4 MTP weight-blocked (GGUF converter dropped nextn tensors). 9 new INVENTORIED roadmap rows value-ordered: SPEC-NGRAM-GPU, SPEC-SUFFIX, SPEC-EAGLE, SPEC-MTP-FAMILY, SPEC-ACCEPT-VARIANTS, SPEC-DYNAMIC, SPEC-CUSTOM-CLASS, SPEC-EXTRACT-HIDDEN, SPEC-MLP-SPECULATOR (upstream-deprecated, completeness). Upstream find: mlp_speculator enum-accepted but V1-dispatch-dead at the pin. Bonus: STATUS compacted (ratchet 287,832 -> 284,329 post-merge).
🤖 Generated with Claude Code
https://claude.ai/code/session_014fZAcg1WcU8V629k6HWKys