Skip to content

Tags: llm-d/llm-d-inference-sim

Tags

v0.10.2

Toggle v0.10.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Revert trigger Trivy scan on PR merge (#584)

Signed-off-by: irar2 <irar@il.ibm.com>

v0.10.1

Toggle v0.10.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
fix: prevent index out-of-range panic when response Strings is an emp…

…ty non-nil slice (#580)

Signed-off-by: irar2 <irar@il.ibm.com>

v0.10.0

Toggle v0.10.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
fix name of usage.prompt_tokens_details (#559)

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

v0.9.2

Toggle v0.9.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
feat: add Mooncake bootstrap /query endpoint (#538)

* feat: add Mooncake bootstrap /query endpoint

- GET /query so the routing sidecar can resolve remote engine_id
for the Mooncake KV connector.
- return dp_rank -> {engine_id} map, seeded uuid per dp rank

Signed-off-by: Wen Zhou <wenzhou@redhat.com>

* update: code review

- generate engine_idis only once to ensure multiple calls return the same
  value
- add a unit test

Signed-off-by: Wen Zhou <wenzhou@redhat.com>

---------

Signed-off-by: Wen Zhou <wenzhou@redhat.com>

v0.9.1

Toggle v0.9.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Support ec_transfer_params in chat completions (#526)

Signed-off-by: irar2 <irar@il.ibm.com>

v0.9.0

Toggle v0.9.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
add features to /inference/v1/generate request and ec_transfer_params…

… to response (#500)

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

v0.9.0-rc3

Toggle v0.9.0-rc3's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
add features to /inference/v1/generate request and ec_transfer_params…

… to response (#500)

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

v0.9.0-rc.2

Toggle v0.9.0-rc.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
change base image (#499)

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

v0.9.0-rc.1

Toggle v0.9.0-rc.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Updates artifacts for v0.9.0-rc.1 release (#487)

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

v0.0.0-test

Toggle v0.0.0-test's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Fix health checks in the disaggregation example (#459)

Signed-off-by: Tamás Lévai <levaitamas@users.noreply.github.com>