Add exact GLM-5.3 DFlash7 Python-overlay runtime - #133
Closed
FujitsuPolycom wants to merge 1 commit into
Closed
Conversation
Construct a DFlash7-labelled image from the shared 31-file vLLM Python overlay while retaining da4d7be native extensions, B12X b1d541f, and SparkCache reconstructed-page placement at 5d571018. Prepared receipts name the external DFlash7 workload and preserve exact source, native, CUDA placement, patch, and lease-contract verification. Add TP4/DCP1 profiles for global safetensors and fastsafetensors. Both use seven DFlash tokens, draft TP4, FP8 target KV, 32 sequences, 256-token blocks, page-tail copy-on-write publication, and canonical SparkCache CUDA restore keys. Safetensors is implemented but unqualified on the composed image; fastsafetensors is research-only pending live draft-loading and peak-memory gates. Cache compatibility: the external DFlash weights digest and page-tail publication schema select a namespace distinct from embedded MTP and snapshot-v1 entries. The two loader profiles share model identity but use separate test roots and clear tokens. No wire value, digest salt, or logical geometry changes. Validation: 24 focused GPU-free tests passed; an exact prepared context verified 31 vLLM files and DFlash7 image labels; Ruff, Python compilation, JSON parsing, Bash syntax, git diff, and prose checks passed. A broader unchanged GLM README assertion remains failing at the stacked base.
Owner
Author
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Result
Adds an exact-contract GLM-5.3 DFlash7 image path and TP4/DCP1 runtime profiles on top of the SparkCache CUDA restore terminology branch.
The image retains vLLM da4d7be native extensions and wheel metadata, overlays the 31 Python files from 0b67266, installs B12X b1d541f, and composes SparkCache reconstructed-page placement at 5d571018. Prepared image labels and receipts identify external DFlash7; they do not claim adaptive MTP.
Profiles
Both profiles use the external DFlash2 weights digest b33c0347, seven speculative tokens, draft TP4, FP8 target KV, 32 sequences, 256-token blocks, page-tail copy-on-write publication, and canonical SparkCache CUDA restore keys.
Compatibility
The DFlash checkpoint digest and page-tail publication schema select a cache namespace distinct from embedded MTP and snapshot-v1 entries. Loader choice does not alter model identity; the two unqualified profiles use separate cache roots and one-shot clear tokens. No wire values, digest salts, or logical geometry change.
Validation
No image was built or published, and no serving host was modified.